© 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. 3917
    Prev
    Next
    INDEX
    Explanations

    various definitions and classifications related to types

    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
    testify
    -0.49
    ArrowToggle
    -0.40
    posedge
    -0.37
     Italijanski
    -0.36
    zarchiwizowane
    -0.36
     <<<<<<<<<<<<<<
    -0.36
    addPreferredGap
    -0.35
    tagHelperRunner
    -0.35
    rxjs
    -0.35
     يتيمه
    -0.35
    POSITIVE LOGITS
    faces
    0.68
     ſta
    0.60
    written
    0.60
    writer
    0.57
     houſe
    0.55
    writers
    0.55
    etting
    0.54
     myſelf
    0.54
     userType
    0.54
     uſe
    0.52
    Activations Density 0.274%

    No Known Activations