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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104709
    Prev
    Next
    INDEX
    Explanations

    references to figures and documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    bootstrapcdn
    -0.57
    SourceChecksum
    -0.50
    AndEndTag
    -0.49
     للمعارف
    -0.49
     Drivers
    -0.49
    Drivers
    -0.48
    ******/
    -0.48
    __);
    -0.48
     pinulongan
    -0.47
    المكان
    -0.47
    POSITIVE LOGITS
    󠁴
    0.38
     pomocy
    0.38
    Demografie
    0.36
    Географија
    0.35
    帖最后由
    0.35
     pudiera
    0.34
     hubiese
    0.33
     suasana
    0.33
     Colin
    0.33
    BufferException
    0.32
    Activations Density 0.033%

    No Known Activations