© 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. 55507
    Prev
    Next
    INDEX
    Explanations

    phrases related to time constraints and limitations

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

    time and space constraints

    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
    暂
    -0.43
     enfans
    -0.35
     appartements
    -0.34
    暂时
    -0.34
     esfuer
    -0.34
     originais
    -0.33
     habet
    -0.32
     Construcción
    -0.31
    ükü
    -0.31
     geprek
    -0.31
    POSITIVE LOGITS
    RegressionTest
    0.66
     "..\..\
    0.64
     Signalez
    0.64
    хьтан
    0.63
    tagHelperRunner
    0.59
    InitVars
    0.59
    Билгалдахарш
    0.57
     الرياضيه
    0.56
     condense
    0.56
    __*/
    0.54
    Activations Density 0.036%

    No Known Activations