© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1444
    Prev
    Next
    INDEX
    Explanations

    phrases related to events and their timings

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

    "At the time of" and subsequent event

    np_acts-logits-general · gemini-2.0-flash

    time of death

    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
    Hentet
    -0.37
     fué
    -0.33
     future
    -0.30
     importanza
    -0.30
    ++];
    -0.27
     débris
    -0.27
     суть
    -0.26
     plata
    -0.26
     other
    -0.26
     iprot
    -0.26
    POSITIVE LOGITS
    parsedMessage
    0.76
     NSCoder
    0.69
    AndEndTag
    0.69
    viewDidLoad
    0.68
    tangentMode
    0.68
    FunctionFlags
    0.65
    migrationBuilder
    0.65
    IContainer
    0.65
    IntoConstraints
    0.64
    EDEFAULT
    0.63
    Activations Density 0.376%

    No Known Activations