© 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. 15-GEMMASCOPE-RES-16K
    11. 3032
    Prev
    Next
    INDEX
    Explanations

    references to ethical approval processes in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.71
    principalTable
    -0.63
    lapsingToolbar
    -0.60
    RetentionPolicy
    -0.54
    \{\\
    -0.54
    stdc
    -0.54
     poffible
    -0.54
    Географиясе
    -0.53
     oprot
    -0.52
     pleaſure
    -0.52
    POSITIVE LOGITS
     id
    0.57
     Nummer
    0.54
     Number
    0.50
     ID
    0.48
    番号
    0.48
     No
    0.47
     Code
    0.47
     №
    0.46
     number
    0.44
    WithIdentifier
    0.44
    Activations Density 1.037%

    No Known Activations