© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7898
    Prev
    Next
    INDEX
    Explanations

    specific names or identifiers related to products or proper nouns

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

    following "ino" or "ne"

    np_acts-logits-general · gemini-2.0-flash

    ino, ne, ene endings (place names, names)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     form
    -0.47
    े
    -0.45
    ي
    -0.43
     partial
    -0.43
    dahl
    -0.42
    ュ
    -0.42
    vious
    -0.41
    chach
    -0.41
    ぁ
    -0.40
               
    -0.40
    POSITIVE LOGITS
     незавершена
    0.99
    
    0.94
     ")");
    0.92
    ibouti
    0.89
    JSONException
    0.86
     GenerationType
    0.83
     autorytatywna
    0.83
    )++;
    0.81
     FetchType
    0.80
     ExecuteAsync
    0.79
    Activations Density 0.446%

    No Known Activations