© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2867
    Prev
    Next
    INDEX
    Explanations

    punctuations and their context in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to personal or identifying details about individuals.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    sentence/paragraph boundaries and nearby date-like years in biographical or narrative passages.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    paragraph or section breaks in formal text, particularly in biographical, legal, or academic writing.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     marginal
    -0.36
    lookup
    -0.36
    тистика
    -0.35
     wajib
    -0.35
    LOOKUP
    -0.34
     so
    -0.33
     translates
    -0.33
     supposedly
    -0.33
    })));
    -0.33
    义
    -0.33
    POSITIVE LOGITS
     StatefulWidget
    0.55
    tagHelperRunner
    0.55
    RTDA
    0.54
    InjectAttribute
    0.54
    transQ
    0.52
     kaarangay
    0.51
     насељу
    0.50
    enumii
    0.49
    #+#
    0.49
    
    0.49
    Activations Density 0.001%

    No Known Activations