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. 7-GEMMASCOPE-RES-16K
    6. 2133
    Prev
    Next
    INDEX
    Explanations

    initialization or procedural commands in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    indications of announcements or declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.58
     CreateTagHelper
    -0.57
     pro
    -0.55
    ########.
    -0.55
    ḵ
    -0.50
    InputBorder
    -0.49
    mfenced
    -0.49
     bo
    -0.46
    )_/¯
    -0.46
    WithFormat
    -0.46
    POSITIVE LOGITS
    */;
    0.72
    complexContent
    0.68
    HomeAsUpEnabled
    0.62
    $',
    0.62
    ])):
    0.62
     houſe
    0.61
    ]));
    
    0.61
    IsContent
    0.60
    $")
    0.59
    )*/
    0.59
    Activations Density 0.291%

    No Known Activations