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. 9-GEMMASCOPE-RES-16K
    6. 15740
    Prev
    Next
    INDEX
    Explanations

    relation to scientific or technical processes, particularly concerning circuits and their efficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.81
    帖最后由
    -0.79
    脚注の使い方
    -0.77
    expandindo
    -0.76
     estekak
    -0.76
    RenderAtEndOf
    -0.75
     виправивши
    -0.73
     lenker
    -0.73
    ##
    
    -0.71
    !';
    -0.70
    POSITIVE LOGITS
    VEND
    0.47
    UrlResolution
    0.47
    angkat
    0.41
    ca
    0.41
    djangoproject
    0.40
    ge
    0.40
    ژه
    0.39
    schedulers
    0.39
     hornblende
    0.39
     تلف
    0.39
    Activations Density 0.078%

    No Known Activations