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. 12-GEMMASCOPE-RES-16K
    6. 6501
    Prev
    Next
    INDEX
    Explanations

    items related to specifications and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HideFlags
    -0.52
    UserScript
    -0.51
    Примечания
    -0.44
    uai
    -0.43
     мѣ
    -0.43
    jsxFileName
    -0.41
     chefe
    -0.41
    差
    -0.41
    元
    -0.41
     العن
    -0.40
    POSITIVE LOGITS
     either
    1.07
     Either
    1.05
    Either
    1.05
    either
    1.04
     entweder
    0.91
     BoxDecoration
    0.88
     cualquiera
    0.77
    ITHER
    0.76
    거나
    0.72
    Datuak
    0.72
    Activations Density 0.525%

    No Known Activations