© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 23677
    Prev
    Next
    INDEX
    Explanations

    terms and functions related to user authentication and environment variable retrieval in code

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

    Username and filenames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simplifié
    -0.51
    SPJ
    -0.48
     createSlice
    -0.45
    ي
    -0.43
    ThroughAttribute
    -0.43
    ewe
    -0.43
    sine
    -0.42
    SizeF
    -0.42
     Sagan
    -0.42
    PhysRev
    -0.42
    POSITIVE LOGITS
    Username
    2.22
     Username
    1.53
    getUsername
    1.31
    setUsername
    1.07
     setUsername
    1.05
    ByUsername
    0.98
     getUsername
    0.96
    USERNAME
    0.91
     usernames
    0.77
    Filename
    0.69
    Activations Density 0.005%

    No Known Activations