Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13270
    Prev
    Next
    INDEX
    Explanations

    snippets of JavaScript code, particularly related to jQuery events and document readiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.63
    SharedCtor
    -0.59
    CompilerServices
    -0.53
    DockStyle
    -0.52
    ########.
    -0.52
     '{@
    -0.51
    TagMode
    -0.51
    
    -0.50
     بيها
    -0.49
    setVerticalGroup
    -0.48
    POSITIVE LOGITS
     arrived
    0.93
     arrival
    0.84
     arrivé
    0.76
     arrives
    0.74
    Arrival
    0.74
    arrival
    0.73
     when
    0.72
     arriving
    0.71
     arrive
    0.71
     Arrived
    0.71
    Activations Density 0.281%

    No Known Activations