© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2698
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to violence and death

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tenth
    -1.26
     Seventy
    -1.23
     Forty
    -1.23
     fourteenth
    -1.22
     Sixty
    -1.21
     Twelfth
    -1.20
     Eighth
    -1.19
     Thirteenth
    -1.19
     Fifty
    -1.18
     Eleventh
    -1.18
    POSITIVE LOGITS
    帖最后由
    0.45
    ❉
    0.43
    Jeografia
    0.40
    ConstraintMaker
    0.39
    addGap
    0.39
     HasFactory
    0.38
     ModelRenderer
    0.36
    ----</
    0.36
    Portail
    0.35
    intios
    0.35
    Activations Density 0.522%

    No Known Activations