© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15047
    Prev
    Next
    INDEX
    Explanations

    nouns and their relationships within a technical or descriptive context

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

    "Hosts", "harbor", “carry”, "contained", or "contains"

    np_acts-logits-general · gemini-2.0-flash

    holding or containing

    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
     تكبرها
    -0.42
    MessageOf
    -0.38
    OGND
    -0.37
     Hitam
    -0.33
    –¿
    -0.32
     döne
    -0.32
     käyt
    -0.32
     Polda
    -0.32
     Masyarakat
    -0.32
     recommandons
    -0.32
    POSITIVE LOGITS
     CreateTagHelper
    0.56
     contains
    0.54
    contains
    0.54
    SequentialGroup
    0.53
    où
    0.52
    BASELINE
    0.52
    setViewportView
    0.52
     '{@
    0.52
    exclusive
    0.52
     contain
    0.52
    Activations Density 0.625%

    No Known Activations