© 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. 33-GEMMASCOPE-RES-16K
    11. 7752
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and logical conditions in a formal or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.53
    CodeAttribute
    -0.53
    MigrationBuilder
    -0.50
     समीक्षाएं
    -0.50
    󠁢
    -0.49
     vPvB
    -0.49
    URLException
    -0.49
    Референ
    -0.49
    ynb
    -0.48
    UrlEncoded
    -0.48
    POSITIVE LOGITS
     —
    0.46
    Véxase
    0.38
     feroit
    0.37
     –
    0.35
     vectorielle
    0.34
     --
    0.33
     -
    0.33
    épreuve
    0.33
    emploi
    0.32
     exécu
    0.31
    Activations Density 0.024%

    No Known Activations