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. 17-GEMMASCOPE-RES-16K
    6. 5772
    Prev
    Next
    INDEX
    Explanations

    terms that indicate degrees of comparison or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hentet
    -0.71
     betegs
    -0.52
     térmico
    -0.52
     financeira
    -0.52
    1
    -0.52
    C
    -0.52
     בב
    -0.51
     skai
    -0.49
    6
    -0.49
    The
    -0.48
    POSITIVE LOGITS
    ".
    
    0.90
     $_"
    0.86
    olesale
    0.83
    */;
    0.82
    ſelves
    0.77
    "):
    
    0.77
    ividual
    0.76
    %"),
    0.76
    lynol
    0.76
    $.
    
    0.75
    Activations Density 0.253%

    No Known Activations