© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 82807
    Prev
    Next
    INDEX
    Explanations

    programming terminology and types in relation to data structures and functions

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

    unsigned integer types

    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
    AddTagHelper
    -0.66
     pleaſure
    -0.63
     mxArray
    -0.60
    المكان
    -0.59
     الرياضيه
    -0.59
    Personendaten
    -0.58
     dalamnya
    -0.56
     purpoſe
    -0.55
    ſelf
    -0.54
    complexContent
    -0.54
    POSITIVE LOGITS
     European
    0.47
    uint
    0.40
     Mah
    0.40
     uint
    0.40
     "
    0.40
    GreaterThan
    0.40
     Czech
    0.40
     French
    0.39
     Dur
    0.38
     dirty
    0.38
    Activations Density 0.010%

    No Known Activations