© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 14
    Prev
    Next
    INDEX
    Explanations

    references to credit or acknowledgement, particularly in the context of film and media productions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewGuid
    -0.42
     Taktlose
    -0.35
    simpleType
    -0.35
     ApiException
    -0.35
    Бахар
    -0.34
    ymce
    -0.34
    PreferredItem
    -0.32
    ChildScrollView
    -0.32
     itemView
    -0.32
     DriverManager
    -0.31
    POSITIVE LOGITS
     credit
    3.59
    credit
    3.16
     Credit
    3.09
    Credit
    3.00
     credits
    3.00
     CREDIT
    2.92
     Credits
    2.72
    CREDIT
    2.66
     credited
    2.61
    credits
    2.56
    Activations Density 0.323%

    No Known Activations