Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-GEMMASCOPE-RES-16K
    6. 3291
    Prev
    Next
    INDEX
    Explanations

    elements related to graphs and their statistical properties

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

    Conditional independence statements

    np_acts-logits-general · gemini-2.0-flash

    virus proteins CI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     posesión
    -0.45
     votación
    -0.43
     húmedo
    -0.42
    исленность
    -0.42
     camioneta
    -0.42
     egens
    -0.42
     leña
    -0.42
     escena
    -0.41
     conservación
    -0.40
     været
    -0.40
    POSITIVE LOGITS
    CI
    1.23
     CI
    1.23
    PI
    1.18
     EI
    1.15
    SI
    1.10
     PI
    1.10
    QI
    1.05
     OI
    1.04
    OI
    1.04
    I
    1.03
    Activations Density 0.833%

    No Known Activations