© 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 - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5633
    Prev
    Next
    INDEX
    Explanations

    specific geographical or demographic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.56
    expandindo
    -0.56
     zoude
    -0.48
     toalha
    -0.47
     enfans
    -0.46
     împre
    -0.45
     demografica
    -0.45
    AddWithValue
    -0.45
    tagHelperRunner
    -0.45
     ainfi
    -0.45
    POSITIVE LOGITS
     bureau
    0.47
    才
    0.44
    orce
    0.44
    cupa
    0.42
     Narayan
    0.42
     Stur
    0.42
    tagens
    0.42
    tahui
    0.41
     trace
    0.41
     Bureau
    0.41
    Activations Density 0.156%

    No Known Activations