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. 20-GEMMASCOPE-RES-16K
    6. 986
    Prev
    Next
    INDEX
    Explanations

    programming constructs and elements related to data types and return statements

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

    Followed by parameters/fields/labels and their types

    np_acts-logits-general · gemini-2.0-flash

    code identifiers

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    endphp
    -0.74
    FunctionFlags
    -0.70
    LookAnd
    -0.68
     utafitiHapana
    -0.67
    oa̍t
    -0.66
    HideFlags
    -0.64
     autorytatywna
    -0.64
     kasarigan
    -0.63
     ब्रेकडाउन
    -0.62
    XmlAccessorType
    -0.60
    POSITIVE LOGITS
    同様に
    0.40
     equally
    0.39
     similarly
    0.37
     wiederum
    0.36
    同样
    0.35
     Sa
    0.35
     incoming
    0.34
     agency
    0.34
     furthermore
    0.34
     lookout
    0.33
    Activations Density 0.366%

    No Known Activations