Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5-GEMMASCOPE-RES-16K
    6. 11062
    Prev
    Next
    INDEX
    Explanations

    references to external links or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.93
    ]='\
    -0.85
    "])
    
    -0.85
    DeleteBehavior
    -0.81
    __":
    
    -0.81
    ]){
    
    -0.79
     mergeFrom
    -0.77
    enumii
    -0.76
    olsom
    -0.75
     Inven
    -0.75
    POSITIVE LOGITS
     here
    1.16
     Here
    1.05
     HERE
    1.04
    here
    0.95
    Here
    0.93
     aquí
    0.90
     acá
    0.84
     aqui
    0.83
     здесь
    0.79
    HERE
    0.77
    Activations Density 0.073%

    No Known Activations