© 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. 31-GEMMASCOPE-RES-16K
    11. 3304
    Prev
    Next
    INDEX
    Explanations

    phrases related to software and system processes

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

    words related to online shopping and product purchasing queries.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     skall
    -0.40
    Grüße
    -0.39
     "...
    -0.37
    ingeki
    -0.37
     تضيفلها
    -0.37
     tidigare
    -0.36
     quizá
    -0.36
     daß
    -0.36
     весьма
    -0.35
     Schluß
    -0.35
    POSITIVE LOGITS
     GREY
    0.78
    endphp
    0.64
    MessageOf
    0.63
     HasFactory
    0.59
    TypedDataSet
    0.59
    кисло
    0.56
    Билгалдахарш
    0.56
     StringTokenizer
    0.54
     airpods
    0.51
     Ncert
    0.50
    Activations Density 0.310%

    No Known Activations