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. 25-GEMMASCOPE-RES-16K
    6. 4319
    Prev
    Next
    INDEX
    Explanations

    programming syntax related to module imports and exports

    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
    JspWriter
    -0.54
    findpost
    -0.53
    uitable
    -0.45
     saying
    -0.44
     dehors
    -0.43
     kteří
    -0.43
    Personendaten
    -0.42
    вига
    -0.42
    Saying
    -0.42
     *>(
    -0.42
    POSITIVE LOGITS
    ########.
    0.80
     فريبيس
    0.66
     nahilalakip
    0.60
     InputDecoration
    0.59
    AddTagHelper
    0.59
     HasFactory
    0.58
    دانشنامهٔ
    0.58
     متعلقه
    0.58
    AndEndTag
    0.56
    ="@+
    0.56
    Activations Density 0.165%

    No Known Activations