© 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. 81644
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the term "parameter" in various contexts

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

    parameter usage

    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
     onCreate
    -0.43
    xmlns
    -0.39
    без
    -0.39
     кли
    -0.38
    printStackTrace
    -0.37
    __'
    -0.36
    frc
    -0.36
    hidup
    -0.35
     Jr
    -0.35
    Blaze
    -0.35
    POSITIVE LOGITS
     parameter
    1.77
    parameter
    1.63
     Parameter
    1.47
     PARAMETER
    1.34
    PARAMETER
    1.13
    Parameter
    1.02
     parametro
    1.01
    getParameter
    0.96
     парамет
    0.90
    ParameterName
    0.88
    Activations Density 0.014%

    No Known Activations