© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 376
    Prev
    Next
    INDEX
    Explanations

    discussion of reasons, purposes, and aspects in research or analysis

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

    Text after ordinal numbers

    np_acts-logits-general · gemini-2.0-flash

    enumeration by first

    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
    migrationBuilder
    -0.63
    twimg
    -0.63
    WireFormatLite
    -0.61
    Chham
    -0.59
    Beispiele
    -0.59
     חיצוניים
    -0.59
    adaptiveStyles
    -0.57
     feveral
    -0.56
    Portail
    -0.54
    iprot
    -0.53
    POSITIVE LOGITS
     first
    2.35
     firstly
    2.19
    Firstly
    2.15
     Firstly
    2.15
    first
    2.02
    First
    1.83
     First
    1.76
     primero
    1.75
     pertama
    1.67
    首先
    1.64
    Activations Density 0.303%

    No Known Activations