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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-GEMMASCOPE-RES-16K
    6. 6237
    Prev
    Next
    INDEX
    Explanations

    references to identification or legal documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſeveral
    -0.77
    "]];
    -0.72
     $_"
    -0.70
     greateſt
    -0.69
     pleaſure
    -0.66
     endfor
    -0.66
     themſelves
    -0.66
     Monfieur
    -0.66
     ſame
    -0.65
    \}\\
    -0.64
    POSITIVE LOGITS
     id
    3.60
     Id
    3.55
     ID
    3.51
    id
    2.83
    Id
    2.81
     IDs
    2.73
    ID
    2.60
     ids
    2.46
     getId
    2.41
    getId
    2.40
    Activations Density 0.139%

    No Known Activations