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. 15-GEMMASCOPE-RES-16K
    6. 12836
    Prev
    Next
    INDEX
    Explanations

    tokens related to code structure and elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.91
    MemoryWarning
    -0.89
     ***!
    -0.80
     Италијани
    -0.78
     mergeFrom
    -0.77
    AsUp
    -0.77
    ]--;
    -0.72
    transQ
    -0.72
    HideFlags
    -0.71
    QMetaType
    -0.70
    POSITIVE LOGITS
    <
    0.79
     IBOutlet
    0.61
    source
    0.59
     <
    0.56
     reason
    0.51
     soft
    0.49
    ><
    0.49
    ;"><
    0.49
     source
    0.48
    runk
    0.48
    Activations Density 0.006%

    No Known Activations