© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 12631
    Prev
    Next
    INDEX
    Explanations

    sections and highlighted or emphasized text within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderRadius
    -0.75
     layui
    -0.67
    inda
    -0.63
    AsUp
    -0.63
    קישורים
    -0.63
    enda
    -0.61
     BoxFit
    -0.60
     isInitialized
    -0.59
     TType
    -0.59
    bilden
    -0.59
    POSITIVE LOGITS
    section
    1.58
    subsubsection
    0.91
    <h2>
    0.87
    subsection
    0.85
    sections
    0.79
     nicio
    0.78
    <h6>
    0.71
    <h1>
    0.70
    <h4>
    0.69
     weevil
    0.69
    Activations Density 0.010%

    No Known Activations