© 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. 24-GEMMASCOPE-RES-16K
    11. 1960
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to statutes or legal procedures

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

    Rules/processes following certain terms

    np_acts-logits-general · gemini-2.0-flash

    established requirements or limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.82
     ujednoznacz
    -0.71
    الحياه
    -0.69
    曖昧さ回避
    -0.68
    
    -0.67
    tagHelperRunner
    -0.64
    AnimationsModule
    -0.56
     виправивши
    -0.55
    Rohy
    -0.55
    مراجع
    -0.54
    POSITIVE LOGITS
     set
    1.67
     established
    1.39
     laid
    1.35
     stipulated
    1.18
    established
    1.11
     outlined
    1.10
     specified
    1.09
    set
    1.09
     prescribed
    1.05
     establecido
    1.05
    Activations Density 0.548%

    No Known Activations