© 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. 38-GEMMASCOPE-RES-16K
    6. 14577
    Prev
    Next
    INDEX
    Explanations

    names of individuals and entities, particularly in legal or official documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erweiterten
    -0.45
    maken
    -0.42
    setu
    -0.34
    setof
    -0.34
    领域的
    -0.33
     sæ
    -0.33
     summers
    -0.32
    Detalles
    -0.32
     peme
    -0.32
    alla
    -0.32
    POSITIVE LOGITS
    writeFieldEnd
    0.74
    oredCriteria
    0.68
    ValueGenerated
    0.65
     OMITBAD
    0.63
    AsNil
    0.63
    windowFixed
    0.61
     Infórmanos
    0.60
    emlrt
    0.60
     oprot
    0.60
    uxxxx
    0.59
    Activations Density 0.611%

    No Known Activations