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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5405
    Prev
    Next
    INDEX
    Explanations

    technical terms and metrics related to mortality and medical conditions

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

    Mathematical or statistical notation/formulae

    np_acts-logits-general · gemini-2.0-flash

    mortality, presumption, NK cells, Omega

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreExecute
    -0.43
    RequestMethod
    -0.41
     calldata
    -0.37
     RequestMethod
    -0.35
    AsUp
    -0.35
    SuppressLint
    -0.34
     FormGroup
    -0.34
    optarg
    -0.32
     season
    -0.32
    dateFormat
    -0.32
    POSITIVE LOGITS
    Autoritní
    0.66
     utafitiHapana
    0.63
    richTextPanel
    0.62
    VYMaps
    0.61
    andExpect
    0.60
     препратки
    0.59
     Baillargeon
    0.58
    يكب
    0.56
     usernames
    0.55
     للاسماء
    0.55
    Activations Density 2.859%

    No Known Activations