© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7114
    Prev
    Next
    INDEX
    Explanations

    the beginning of a narrative or a significant event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.59
     humaine
    -0.58
     quæ
    -0.55
    kkelen
    -0.55
     ſhould
    -0.50
    sizeCache
    -0.49
     régionale
    -0.48
     bune
    -0.48
     umani
    -0.48
     umana
    -0.47
    POSITIVE LOGITS
    <bos>
    1.06
     EconPapers
    0.84
     فريبيس
    0.73
    campal
    0.61
    ArgsConstructor
    0.60
    ewear
    0.59
    ?>">
    0.59
    最快更新
    0.59
     oprot
    0.58
    didSet
    0.58
    Activations Density 0.748%

    No Known Activations