© 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. 25-GEMMASCOPE-RES-16K
    6. 15340
    Prev
    Next
    INDEX
    Explanations

    key terms related to legal proceedings and criminal actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gweler
    -0.43
     Wachs
    -0.40
     estekak
    -0.38
    videz
    -0.38
    Desen
    -0.37
     ویکی‌پدی
    -0.36
    Enllaces
    -0.36
    rzost
    -0.35
    withOpacity
    -0.35
     golfe
    -0.35
    POSITIVE LOGITS
     Chwiliwch
    0.49
     Infórmanos
    0.47
     Paglinawan
    0.42
    rrggbb
    0.42
    rungsseite
    0.42
    AndFlush
    0.40
     @"/
    0.40
    MLLoader
    0.39
     nahilalakip
    0.39
    Sucesor
    0.38
    Activations Density 0.532%

    No Known Activations