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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4500
    Prev
    Next
    INDEX
    Explanations

    terms related to connections and associations

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

    "Related" and subsequent topics

    np_acts-logits-general · gemini-2.0-flash

    related events, articles, art, posts, companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.54
    uxxxx
    -0.52
     Paglinawan
    -0.49
    SharedDtor
    -0.47
     Италијани
    -0.45
    ➌
    -0.43
    KommentareTeilen
    -0.43
    InjectAttribute
    -0.40
    __(/*!
    -0.40
    UserScript
    -0.39
    POSITIVE LOGITS
    Relation
    0.56
     matters
    0.54
     QtCore
    0.53
     issues
    0.52
     erat
    0.51
     relate
    0.51
     Beziehungen
    0.51
    related
    0.51
    Related
    0.50
    relate
    0.50
    Activations Density 0.201%

    No Known Activations