© 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. 13492
    Prev
    Next
    INDEX
    Explanations

    references to technology and programming

    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
    Personendaten
    -0.59
    뀜
    -0.58
    帖最后由
    -0.56
     surla
    -0.53
     MainAxisSize
    -0.52
    ftagPool
    -0.52
    principalColumn
    -0.50
     nahilalakip
    -0.50
     informée
    -0.49
    verwijspagina
    -0.49
    POSITIVE LOGITS
     look
    3.58
     looks
    3.23
    look
    3.14
     Look
    3.02
    Look
    2.95
     looked
    2.81
     LOOK
    2.81
    looks
    2.73
    LOOK
    2.69
     Looks
    2.66
    Activations Density 1.409%

    No Known Activations