© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11355
    Prev
    Next
    INDEX
    Explanations

    legal terms and references to criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal trials and juries

    np_acts-logits-general · gemini-2.0-flash

    jury trial verdict

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.76
    stateMutability
    -0.67
     Schreiben
    -0.57
     letter
    -0.57
    uluş
    -0.55
     ngào
    -0.51
     Zuw
    -0.49
     lettera
    -0.46
     Enforcement
    -0.46
    Enforcement
    -0.46
    POSITIVE LOGITS
     trial
    1.49
     jury
    1.38
    Trial
    1.30
    trial
    1.27
     TRIAL
    1.25
     Trial
    1.25
     jurors
    1.16
    Jury
    1.15
     trials
    1.11
     Jury
    1.10
    Activations Density 1.393%

    No Known Activations