Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68315
    Prev
    Next
    INDEX
    Explanations

    keywords related to system runtime and security in programming contexts

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

    runtime and security

    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
    expandindo
    -0.65
    RegressionTest
    -0.65
    AndEndTag
    -0.64
    ⓧ
    -0.63
     HasFactory
    -0.61
     createSlice
    -0.61
    oredCriteria
    -0.56
    олові
    -0.56
    ConstraintMaker
    -0.54
    esModule
    -0.54
    POSITIVE LOGITS
    Runtime
    1.04
     Runtime
    0.69
     runtime
    0.59
    runtime
    0.54
    RUNTIME
    0.50
    InteropServices
    0.48
     vectorielles
    0.47
     Monfieur
    0.44
     chevalier
    0.43
     elef
    0.43
    Activations Density 0.000%

    No Known Activations