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. 9812
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to biological processes and gene ontology

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

    Preceding terms related to contracts or legal documents

    np_acts-logits-general · gemini-2.0-flash

    regulation, sale, intelligent, waiver

    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
     يتيمه
    -0.66
    !*\
    -0.54
     Photocase
    -0.53
    kuuta
    -0.53
    ISupport
    -0.47
    tvguidetime
    -0.46
    MLLoader
    -0.46
     CWE
    -0.45
    principalColumn
    -0.45
    Gön
    -0.43
    POSITIVE LOGITS
    enderror
    0.54
    aarrggbb
    0.52
    AnchorTagHelper
    0.48
    RectangleBorder
    0.43
    CardHeader
    0.40
    AsUp
    0.40
     AssemblyVersion
    0.40
    exitRule
    0.38
    CardContent
    0.38
     encant
    0.38
    Activations Density 1.177%

    No Known Activations