© 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. 101090
    Prev
    Next
    INDEX
    Explanations

    numerical values and references to game mechanics related to leveling and quests

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

    level, levels, leveling

    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
    XmlAccessorType
    -0.65
     ब्रेकडाउन
    -0.64
     @"/
    -0.63
    enumii
    -0.63
     OMITBAD
    -0.58
    ⤹
    -0.54
    writeFieldEnd
    -0.53
    MessageOf
    -0.52
     للاسماء
    -0.52
     OMIT
    -0.52
    POSITIVE LOGITS
     level
    0.68
     grade
    0.64
     lvl
    0.57
     nivel
    0.56
     Level
    0.53
    Level
    0.52
    level
    0.52
    级
    0.52
    Lvl
    0.51
     niveau
    0.51
    Activations Density 0.007%

    No Known Activations