© 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. 37-GEMMASCOPE-RES-16K
    6. 909
    Prev
    Next
    INDEX
    Explanations

    code-related terms and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     D
    -2.25
    D
    -1.77
     d
    -1.73
    getD
    -1.32
     د
    -1.24
    d
    -1.20
     Д
    -1.17
     д
    -1.10
    D
    -1.00
    Д
    -0.94
    POSITIVE LOGITS
    dog
    0.44
     CURIAM
    0.44
    deja
    0.41
    principalTable
    0.41
    rawDesc
    0.40
    .*")]
    0.40
    deer
    0.39
    oredCriteria
    0.39
    ftagPool
    0.39
    complexContent
    0.39
    Activations Density 1.639%

    No Known Activations