© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2982
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to legislative intent and defendant rights

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

    elements of legal language related to sentencing and the appropriateness of evidence presented in court

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 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
    ↵
    -0.53
     @
    -0.53
    municipi
    -0.44
     is
    -0.43
     normal
    -0.42
    ↵↵↵
    -0.42
     fine
    -0.42
     for
    -0.41
    ratto
    -0.39
     the
    -0.38
    POSITIVE LOGITS
    httphttps
    0.96
     nakalista
    0.83
    [toxicity=0]
    0.82
    +:+
    0.81
     AttributeSet
    0.80
     BoxFit
    0.80
    __(/*!
    0.78
     الحره
    0.76
    AlterField
    0.73
    MemoryWarning
    0.71
    Activations Density 0.060%

    No Known Activations