© 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. 4-GEMMASCOPE-RES-16K
    11. 397
    Prev
    Next
    INDEX
    Explanations

    terms related to legal charges and criminal offenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Perspek
    -0.59
    Нам
    -0.57
    matically
    -0.56
    atly
    -0.54
     raste
    -0.54
    czki
    -0.54
    Amicalement
    -0.54
    urably
    -0.54
    hatt
    -0.53
    ICALLY
    -0.53
    POSITIVE LOGITS
     robbery
    0.77
    murder
    0.74
     assassination
    0.73
     monoxide
    0.73
     murder
    0.71
     Murder
    0.69
    Murder
    0.67
     assassins
    0.66
    PropertyGroup
    0.65
     murderers
    0.65
    Activations Density 2.605%

    No Known Activations