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. 8078
    Prev
    Next
    INDEX
    Explanations

    various types of programming syntax, particularly related to method calls and assignments

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

    Java-related code or expressions

    np_acts-logits-general · gemini-2.0-flash

    java code syntax

    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
     [`
    -0.67
     $[
    -0.65
    [,]
    -0.63
     {:
    -0.62
    ::{
    -0.61
     يتيمه
    -0.60
     [_
    -0.59
     [$
    -0.59
    =['
    -0.59
    djangoproject
    -0.59
    POSITIVE LOGITS
    Integer
    1.00
     Integer
    0.98
     Collections
    0.95
     Arrays
    0.92
     new
    0.92
    new
    0.91
    null
    0.84
    System
    0.81
    Collections
    0.81
    Arrays
    0.81
    Activations Density 0.127%

    No Known Activations