Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6043
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce or reference previous statements or claims

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

    Follows reporting verbs

    np_acts-logits-general · gemini-2.0-flash

    referencing or citing sources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     where
    -0.48
    ');
    -0.43
    .
    -0.42
    big
    -0.41
    ').
    -0.41
     donde
    -0.41
    '.
    -0.41
     that
    -0.41
    +#+
    -0.40
     which
    -0.40
    POSITIVE LOGITS
    Lähteet
    0.81
    __':
    
    0.81
     الرياضيه
    0.80
     muualla
    0.79
    Bronnen
    0.79
    הערות
    0.77
    AndEndTag
    0.75
     BoxFit
    0.75
    évaluateur
    0.73
    __":
    
    0.73
    Activations Density 0.204%

    No Known Activations