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. 6-GEMMASCOPE-RES-16K
    6. 436
    Prev
    Next
    INDEX
    Explanations

    inquiries related to mathematical comparisons and classifications of value

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    programming-related or technical query language involving verbs like move, provide, understand, and discuss programming concepts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nemlig
    -0.64
    RenderAtEndOf
    -0.61
     Савезне
    -0.60
    esModule
    -0.59
     بيها
    -0.57
    retudo
    -0.57
    smithy
    -0.57
    wenye
    -0.56
    følgelig
    -0.56
    日閲覧
    -0.55
    POSITIVE LOGITS
    ?
    1.18
    ?”
    1.18
    ?"
    1.06
    ?)
    0.95
    ?}
    0.95
    ؟
    0.93
    ?“
    0.92
    ?</
    0.91
    ?”.
    0.91
    ?:
    0.90
    Activations Density 0.941%

    No Known Activations