© 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. 31-GEMMASCOPE-RES-131K
    11. 12721
    Prev
    Next
    INDEX
    Explanations

    intensifiers or modifiers that amplify the degree of a quality

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

    very followed by a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.56
     SwitchCompat
    -0.52
    scut
    -0.44
    Kend
    -0.40
    Composable
    -0.39
    ScopeManager
    -0.38
     sepenuhnya
    -0.38
    SharedModule
    -0.38
    CDS
    -0.38
     Coder
    -0.38
    POSITIVE LOGITS
    stdarg
    0.64
     much
    0.63
    ">//
    0.60
     important
    0.56
     well
    0.54
    yyyy
    0.54
     mực
    0.53
    Molto
    0.53
    ymce
    0.52
     good
    0.51
    Activations Density 0.035%

    No Known Activations