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. 5-GEMMASCOPE-RES-16K
    6. 12252
    Prev
    Next
    INDEX
    Explanations

    hexadecimal color codes and related numerical values in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResumeLayout
    -0.82
    ContentAsync
    -0.79
     zvuky
    -0.72
     Процитовано
    -0.72
    Datuak
    -0.69
    CodeAttribute
    -0.69
    preventDefault
    -0.69
    клопе
    -0.68
    存于互联网档案馆
    -0.64
     lenker
    -0.64
    POSITIVE LOGITS
    xff
    1.93
    xFF
    1.46
    xffffffff
    0.79
    xFFFF
    0.79
    ագրություններ
    0.78
    XFF
    0.77
    xffff
    0.73
    xfe
    0.72
    Errorf
    0.71
    </tfoot>
    0.71
    Activations Density 0.030%

    No Known Activations