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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 66604
    Prev
    Next
    INDEX
    Explanations

    data types and variable declarations in programming code

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

    long unsigned int

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ToAction
    -0.39
    .
    -0.38
    makeText
    -0.36
     
    -0.34
    -0.34
     dotyczy
    -0.33
    If
    -0.33
    ecap
    -0.33
    In
    -0.33
    :=
    -0.33
    POSITIVE LOGITS
     pinulongan
    0.81
     Taktlose
    0.74
    ̈́
    0.71
    تقاوى
    0.71
    الحياه
    0.69
    WriteTagHelper
    0.66
    Cyfarwyddwr
    0.62
    awtextra
    0.57
     Administrativna
    0.56
    fromnode
    0.55
    Activations Density 0.036%

    No Known Activations