© 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. 37-GEMMASCOPE-RES-16K
    11. 4925
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "ver" (to see) in German

    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
    arangay
    -0.59
     Bewußt
    -0.52
     ProtoMessage
    -0.50
    rungsseite
    -0.50
    ėse
    -0.50
    Besitos
    -0.50
     haji
    -0.50
     pisau
    -0.48
     manguera
    -0.48
     huesos
    -0.48
    POSITIVE LOGITS
    ContentAsync
    0.42
    interopRequire
    0.41
    urs
    0.37
    金
    0.37
    ">//
    0.35
     Pov
    0.34
     فر
    0.34
     tang
    0.33
    NU
    0.33
    mstyle
    0.33
    Activations Density 0.131%

    No Known Activations