Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 25-GEMMASCOPE-RES-16K
    6. 5948
    Prev
    Next
    INDEX
    Explanations

    terms related to events and studies, particularly in a research or academic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wicidata
    -0.63
    setof
    -0.63
    offsetof
    -0.63
    addPreferredGap
    -0.60
    colgroup
    -0.59
    makeConstraints
    -0.59
    TagMode
    -0.57
    JspWriter
    -0.56
    TabIndex
    -0.54
    NameInMap
    -0.52
    POSITIVE LOGITS
     itself
    1.55
     Itself
    1.06
    itself
    1.05
     itſelf
    0.87
     itse
    0.82
     stessa
    0.78
     structure
    0.78
    本身
    0.77
    টি
    0.76
     stesso
    0.71
    Activations Density 1.032%

    No Known Activations