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-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 11287
    Prev
    Next
    INDEX
    Explanations

    specific terms related to documentation in a software or coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 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
    <bos>
    -0.49
    arangay
    -0.46
     lehetős
    -0.45
     okuyayım
    -0.44
     étoient
    -0.44
     siedz
    -0.43
     bēr
    -0.42
    pośred
    -0.42
     avoient
    -0.40
     stället
    -0.40
    POSITIVE LOGITS
    忑
    0.73
     للاسماء
    0.63
    原始内容存档于
    0.56
    UIControlState
    0.55
    __*/
    0.54
    ViewFeatures
    0.53
    endpush
    0.51
    });*/
    0.50
    </tfoot>
    0.50
    EndInit
    0.49
    Activations Density 0.112%

    No Known Activations