© 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. 2-GEMMASCOPE-RES-16K
    6. 12863
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cuts" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     armat
    -0.40
     enums
    -0.39
    ніципалі
    -0.37
     honey
    -0.36
     mobiles
    -0.35
     Calend
    -0.35
    ußt
    -0.35
     bio
    -0.34
     conver
    -0.34
     Eud
    -0.34
    POSITIVE LOGITS
     cuts
    1.22
     hits
    1.20
     strokes
    1.20
     shots
    1.20
    shots
    1.16
     blows
    1.15
     bites
    1.14
     Shots
    1.13
     touches
    1.13
    cuts
    1.09
    Activations Density 0.280%

    No Known Activations