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. 31-GEMMASCOPE-RES-16K
    6. 16343
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data structure properties and statistical parameters

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

    Shader file extensions and padding

    np_acts-logits-general · gemini-2.0-flash

    Diastolic specificity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tembelea
    -0.78
    󠁴
    -0.67
     MenuView
    -0.65
     الرياضيه
    -0.63
    botto
    -0.53
    ThroughAttribute
    -0.52
     monog
    -0.52
     noDo
    -0.52
     nic
    -0.52
     bache
    -0.52
    POSITIVE LOGITS
     keduanya
    0.53
     duradero
    0.49
     selben
    0.47
     térmico
    0.47
     respectivamente
    0.45
     counterpart
    0.45
     respectivas
    0.45
     båda
    0.45
     соответственно
    0.44
     cheminée
    0.44
    Activations Density 3.247%

    No Known Activations