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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15108
    Prev
    Next
    INDEX
    Explanations

    mentions of versioning and version numbers in various contexts

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

    "version" followed by punctuation or code

    np_acts-logits-general · gemini-2.0-flash

    version

    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
     Gual
    -0.50
    adalajara
    -0.49
    __":
    -0.49
    Ground
    -0.48
    dflare
    -0.48
    Früh
    -0.47
     Schmel
    -0.47
     Alicante
    -0.47
     Charities
    -0.46
    Leuk
    -0.46
    POSITIVE LOGITS
     version
    1.42
     Version
    1.38
    version
    1.35
    Version
    1.31
     VERSION
    1.25
    getVersion
    1.19
     getVersion
    1.15
     versions
    1.14
    VERSION
    1.09
     Versions
    1.06
    Activations Density 0.068%

    No Known Activations