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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6757
    Prev
    Next
    INDEX
    Explanations

    verbs indicating decisions or choices being made

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     movi
    -0.36
    Weblinks
    -0.35
     capacity
    -0.35
     minuta
    -0.35
     kny
    -0.35
     exac
    -0.34
     errors
    -0.34
     mastery
    -0.34
    Errors
    -0.33
    Already
    -0.33
    POSITIVE LOGITS
    styleType
    0.78
     decided
    0.76
    decided
    0.73
     opted
    0.71
     chose
    0.67
    ftagPool
    0.66
     decidido
    0.66
    WriteBarrier
    0.66
    EDEFAULT
    0.65
    chose
    0.65
    Activations Density 0.367%

    No Known Activations