© 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. 4-GEMMASCOPE-RES-16K
    11. 16118
    Prev
    Next
    INDEX
    Explanations

    boolean attributes in markup or programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oldown
    -0.63
     <>",
    -0.63
    wness
    -0.58
    wurst
    -0.58
    ngth
    -0.57
     us
    -0.57
    embatan
    -0.57
    vyš
    -0.56
    phorbia
    -0.56
    fillType
    -0.56
    POSITIVE LOGITS
    true
    2.08
     true
    1.53
    True
    1.40
    TRUE
    1.35
     True
    1.23
     TRUE
    1.19
    false
    1.05
     verdadeira
    1.02
     truer
    1.02
     verdadeiro
    1.02
    Activations Density 0.131%

    No Known Activations