© 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. 8293
    Prev
    Next
    INDEX
    Explanations

    technical terms related to coding or system errors

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

    Numbers followed or preceded by colons or other number-related tokens

    np_acts-logits-general · gemini-2.0-flash

    rectangle(( or concluded that

    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
    众
    -0.50
     Cole
    -0.48
    mtable
    -0.47
    RuleContext
    -0.46
    ledo
    -0.46
    可怜
    -0.46
    
    -0.45
     Савезне
    -0.45
     nome
    -0.45
    tro
    -0.44
    POSITIVE LOGITS
    tvguidetime
    0.94
    rrggbb
    0.86
    InstanceState
    0.72
    ConstraintMaker
    0.70
     CURIAM
    0.66
    ViewInit
    0.62
    ressee
    0.61
     itſelf
    0.61
    rubber
    0.59
    ształ
    0.58
    Activations Density 0.264%

    No Known Activations