© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 8958
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes related to linking and sourcing images and files

    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
     <=",
    -0.89
    DeleteBehavior
    -0.74
     wireType
    -0.70
    %)$
    -0.70
     صوتيه
    -0.69
    DoubleQuotes
    -0.68
    ]")]
    -0.68
    LookAnd
    -0.67
     &___
    -0.66
    addCriterion
    -0.65
    POSITIVE LOGITS
     "..\..\..\
    0.68
     "..\..\
    0.61
     насељу
    0.53
     resor
    0.52
    paddingTop
    0.49
    τηση
    0.47
     Coma
    0.47
    最快更新
    0.47
    Bibliograf
    0.45
     kine
    0.43
    Activations Density 0.462%

    No Known Activations