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. 7394
    Prev
    Next
    INDEX
    Explanations

    references to film production and direction

    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
    Clik
    -0.68
    apnews
    -0.66
    amssymb
    -0.56
     itſelf
    -0.54
     rück
    -0.54
     SqlDbType
    -0.53
     currentValue
    -0.53
     Träger
    -0.53
    ]='\
    -0.52
     propOrder
    -0.52
    POSITIVE LOGITS
    VersionUID
    0.72
    CodedInputStream
    0.69
    Expedia
    0.54
     faciliter
    0.53
     supervision
    0.52
    TODOS
    0.49
    CloseOperation
    0.49
     Supervision
    0.49
    jutant
    0.48
    Referensi
    0.48
    Activations Density 0.247%

    No Known Activations