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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9885
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to isolation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oneph
    -0.69
    huff
    -0.61
    k
    -0.60
    CardContent
    -0.59
    StoredProcedure
    -0.57
    AnimationsModule
    -0.57
     cref
    -0.57
    Parameteri
    -0.56
     keb
    -0.55
    ke
    -0.55
    POSITIVE LOGITS
     isolation
    3.27
     Isolation
    3.15
     isolated
    3.07
     Isolated
    3.04
    isolated
    2.95
     isolate
    2.94
    Isolation
    2.89
    Isolated
    2.88
     ISOL
    2.87
     isolating
    2.84
    Activations Density 0.131%

    No Known Activations