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. 15-GEMMASCOPE-RES-16K
    6. 1879
    Prev
    Next
    INDEX
    Explanations

    references to warnings or preventive measures regarding potential threats or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 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
    ArgsConstructor
    -0.56
    GenerationType
    -0.56
     BorderSide
    -0.53
    zol
    -0.50
    windowFixed
    -0.50
    printStackTrace
    -0.49
     تعريف
    -0.48
    $=\
    -0.47
    itzenden
    -0.47
    ypeł
    -0.47
    POSITIVE LOGITS
     warnings
    1.34
     warned
    1.33
     warning
    1.30
     warn
    1.12
     Warnings
    1.08
     foresight
    1.05
    warnings
    1.04
     warns
    1.04
     Warning
    1.02
    warn
    1.00
    Activations Density 0.288%

    No Known Activations