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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14642
    Prev
    Next
    INDEX
    Explanations

    programming-related constructs, focusing on function definitions and variable assignments

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

    code-like constructs, especially C/Objective‑C method signatures and preprocessor macros, along with structured read/write or debug log statements.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.99
    хьтан
    -0.88
     betweenstory
    -0.87
    NewUrlParser
    -0.85
     CanadaChoose
    -0.84
    yntaxException
    -0.84
     Biôgrafia
    -0.82
    protoimpl
    -0.81
     ویکی‌پدی
    -0.81
    تقاوى
    -0.81
    POSITIVE LOGITS
     correspondiente
    0.36
     corresponding
    0.33
     khusus
    0.31
    fc
    0.30
     «
    0.30
    对应的
    0.28
     the
    0.27
     then
    0.27
     done
    0.27
     subsequently
    0.27
    Activations Density 0.368%

    No Known Activations