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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3722
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements and conditional checks in code

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

    Code syntax and related terms

    np_acts-logits-general · gemini-2.0-flash

    code, test, and programming syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astify
    -0.69
     חיצוניים
    -0.66
    ioutil
    -0.63
    DockStyle
    -0.59
    MessageTagHelper
    -0.57
     ConstraintSet
    -0.55
    GOTREF
    -0.55
     onPostExecute
    -0.55
    UnusedPrivate
    -0.55
     
    -0.52
    POSITIVE LOGITS
     colores
    0.47
     pieles
    0.45
     genre
    0.45
     armario
    0.43
     huéspedes
    0.42
     sahibi
    0.42
     niche
    0.42
    :✨
    0.41
     género
    0.41
     naciones
    0.41
    Activations Density 1.188%

    No Known Activations