© 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. 5495
    Prev
    Next
    INDEX
    Explanations

    keywords and attributes related to programming, particularly in context of data structures and properties in code

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

    Boolean values and related terms

    np_acts-logits-general · gemini-2.0-flash

    true or false values

    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
    例句
    -0.60
    ächtigen
    -0.51
     sinner
    -0.48
     ModelRenderer
    -0.48
    __["
    -0.46
     gynhyrchwyd
    -0.45
    )‏
    -0.45
    Compat
    -0.45
    させて頂きます
    -0.44
     digress
    -0.43
    POSITIVE LOGITS
     true
    2.20
     True
    2.11
    true
    2.10
    True
    2.03
     TRUE
    1.99
     false
    1.99
     False
    1.98
    TRUE
    1.91
    False
    1.86
    false
    1.86
    Activations Density 0.508%

    No Known Activations