© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80575
    Prev
    Next
    INDEX
    Explanations

    programming concepts and structures related to class definitions and attributes in code

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

    percentage values in code

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    StoryboardSegue
    -0.72
    AndEndTag
    -0.64
     utafitiHapana
    -0.60
    Personendaten
    -0.59
    帖最后由
    -0.57
    期刊论文
    -0.57
    tagext
    -0.54
     StringTokenizer
    -0.54
     CanadaChoose
    -0.54
     ExecuteAsync
    -0.51
    POSITIVE LOGITS
     ddelweddau
    0.47
     legislación
    0.35
     protección
    0.34
     offent
    0.33
    BeNil
    0.33
     Waray
    0.32
    DataAnnotations
    0.32
     normalidad
    0.32
     arrangement
    0.31
     ucran
    0.31
    Activations Density 0.000%

    No Known Activations