© 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
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 6006
    Prev
    Next
    INDEX
    Explanations

    references to support services and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Билгалдахарш
    -0.30
    ulha
    -0.30
     lắm
    -0.30
    INTERRUPT
    -0.30
     casual
    -0.30
     useStyles
    -0.29
     untreated
    -0.29
     Proced
    -0.29
    borderSide
    -0.29
     Tiro
    -0.29
    POSITIVE LOGITS
    webElement
    0.65
     kasarigan
    0.62
     linkovi
    0.60
    bootstrapcdn
    0.55
     ModelExpression
    0.55
     محفوظة
    0.53
    AsUp
    0.52
    +#+
    0.51
    titia
    0.51
    enumii
    0.51
    Activations Density 0.351%

    No Known Activations