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. 3570
    Prev
    Next
    INDEX
    Explanations

    significant references to quantitative measurements and evaluations in various contexts

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

    Adverbs modifying the degree of an adjective

    np_acts-logits-general · gemini-2.0-flash

    high degree

    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
    UnitTesting
    -0.61
    ंदीखरीदारी
    -0.60
    InjectAttribute
    -0.56
    UserScript
    -0.54
    Diwedd
    -0.52
     SwitchCompat
    -0.52
    abatic
    -0.51
    Composable
    -0.50
    endforeach
    -0.49
    ⟬
    -0.49
    POSITIVE LOGITS
     מאוד
    0.81
     Very
    0.68
     very
    0.66
    Very
    0.64
     highly
    0.60
    Molto
    0.59
     banget
    0.59
     Many
    0.59
     heavily
    0.57
     Highly
    0.56
    Activations Density 0.968%

    No Known Activations