© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 1996
    Prev
    Next
    INDEX
    Explanations

    chemical and biological terms or compounds

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

    ending in "ine" or "in"

    np_acts-logits-general · gemini-2.0-flash

    volvocine

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     purpoſe
    -0.69
     pleaſure
    -0.62
    nthesis
    -0.58
    ValueStyle
    -0.56
     Autorizaciones
    -0.56
    CppCodeGen
    -0.56
     onely
    -0.55
     ſte
    -0.54
     ſch
    -0.54
     beſt
    -0.54
    POSITIVE LOGITS
    ine
    0.86
    ina
    0.82
    in
    0.77
    ins
    0.76
    IN
    0.75
    ino
    0.75
    rin
    0.75
    alin
    0.74
    lin
    0.72
    ín
    0.71
    Activations Density 2.880%

    No Known Activations