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. 24-GEMMASCOPE-RES-16K
    6. 2380
    Prev
    Next
    INDEX
    Explanations

    CSS style attributes and their properties in markup

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

    CSS styling attributes

    np_acts-logits-general · gemini-2.0-flash

    css layout properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jsPsych
    -0.63
    ExecuteReader
    -0.58
    oznam
    -0.58
    getValueAt
    -0.58
    ::$_
    -0.57
    üyada
    -0.57
    Handlung
    -0.55
    RUnlock
    -0.54
    BindingResult
    -0.54
    dpa
    -0.53
    POSITIVE LOGITS
    width
    0.88
     width
    0.84
    margin
    0.83
     margin
    0.79
    padding
    0.79
    height
    0.76
     padding
    0.74
     height
    0.70
    position
    0.63
    float
    0.60
    Activations Density 0.073%

    No Known Activations