© 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. 1-GEMMASCOPE-RES-16K
    11. 10528
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of safety, ease, and happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    böz
    -0.50
    ViewChild
    -0.46
    VarChar
    -0.44
    tagHelper
    -0.43
    addPreferredGap
    -0.43
    تیب
    -0.42
     sight
    -0.42
     IGN
    -0.42
     joy
    -0.42
     PUR
    -0.41
    POSITIVE LOGITS
     safer
    1.50
     safest
    1.39
     healthier
    1.32
     happier
    1.25
     healthiest
    1.21
     cleanest
    1.18
    easier
    1.17
     clearer
    1.16
     smarter
    1.14
     funnier
    1.11
    Activations Density 0.164%

    No Known Activations