© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 381
    Prev
    Next
    INDEX
    Explanations

    references to visual display characteristics and factors affecting visibility

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

    Tokens preceding conditional statements or alternative options

    np_acts-logits-general · gemini-2.0-flash

    otherwise, else

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    şört
    -0.65
    évaluateur
    -0.65
     CreateTagHelper
    -0.63
    hoeddwyd
    -0.63
     noDo
    -0.63
     كومونز
    -0.62
    windowFixed
    -0.60
     fieldNum
    -0.59
    AsUp
    -0.58
     Савезне
    -0.58
    POSITIVE LOGITS
     otherwise
    0.33
    else
    0.32
    untergang
    0.30
    Else
    0.28
     Kors
    0.27
     else
    0.27
    glMatrixMode
    0.27
     Tib
    0.26
    printStackTrace
    0.26
     Royal
    0.26
    Activations Density 0.604%

    No Known Activations