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. 17-GEMMASCOPE-RES-16K
    6. 1149
    Prev
    Next
    INDEX
    Explanations

    instances of narrative quotes or commentary in the text

    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
    usermodel
    -0.64
    lapsingToolbar
    -0.64
    нда
    -0.62
    ogram
    -0.59
     للمعارف
    -0.56
    lblNewLabel
    -0.55
    </b>
    -0.55
    서는
    -0.55
    BRON
    -0.54
    archical
    -0.54
    POSITIVE LOGITS
    ."""
    1.33
    """
    1.31
     """
    1.24
    __*/
    1.03
    httphttps
    0.98
    ("""
    0.95
     ***!
    0.94
     """
    
    0.92
     quæ
    0.86
    SourceChecksum
    0.84
    Activations Density 0.092%

    No Known Activations