© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 883
    Prev
    Next
    INDEX
    Explanations

    expressions of fatalism and concepts of divine punishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.76
     BoxFit
    -0.63
    nextSibling
    -0.63
    RenderAtEndOf
    -0.63
    躇
    -0.60
    endphp
    -0.59
    ArgsConstructor
    -0.58
    HostException
    -0.55
    (&:
    -0.55
     Monfieur
    -0.54
    POSITIVE LOGITS
     message
    0.61
     messaggio
    0.59
     messaggi
    0.58
     signal
    0.56
    メッセージ
    0.55
     muualla
    0.54
     signals
    0.53
    typeorm
    0.52
     kasarigan
    0.52
     messages
    0.52
    Activations Density 0.197%

    No Known Activations