© 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. 20-GEMMASCOPE-RES-16K
    11. 292
    Prev
    Next
    INDEX
    Explanations

    mentions of formal statements, declarations, or assertions

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

    "statement" or "statements"

    np_acts-logits-general · gemini-2.0-flash

    statements and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    didSet
    -0.84
    IContainer
    -0.57
    gebracht
    -0.55
    seteq
    -0.50
    Kno
    -0.50
    CGContext
    -0.49
     FetchType
    -0.49
    cstdlib
    -0.48
    kno
    -0.47
    snip
    -0.47
    POSITIVE LOGITS
     statements
    0.96
    stmt
    0.96
     Statements
    0.90
    Gambas
    0.84
     declarations
    0.84
     statement
    0.83
     declares
    0.82
     Declare
    0.81
     declaring
    0.78
     declaration
    0.78
    Activations Density 0.158%

    No Known Activations