© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5800
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "few."

    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
    GenerationType
    -0.50
    GeneratedMessage
    -0.45
     مشين
    -0.44
    WritableDatabase
    -0.44
    zungs
    -0.40
    ectoria
    -0.40
    tissement
    -0.40
    tisation
    -0.38
     CRI
    -0.38
     همچنین
    -0.37
    POSITIVE LOGITS
     few
    3.80
    Few
    3.53
    few
    3.38
     Few
    3.34
     FEW
    2.80
     pocos
    2.33
     poucos
    2.23
     pochi
    2.16
     pocas
    2.11
     wenigen
    2.06
    Activations Density 0.056%

    No Known Activations