© 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. 10714
    Prev
    Next
    INDEX
    Explanations

    terms related to timing and early actions or events

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

    "too early" or "before expected time"

    np_acts-logits-general · gemini-2.0-flash

    early or premature events

    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
     inflación
    -0.40
    encodeWith
    -0.36
    PyErr
    -0.36
    tgär
    -0.35
     Shand
    -0.33
     cadastro
    -0.32
     hậu
    -0.32
     OMITTED
    -0.32
    hmig
    -0.31
     berk
    -0.30
    POSITIVE LOGITS
     premature
    0.88
     prematurely
    0.84
     accelerated
    0.69
     early
    0.65
     EARLY
    0.63
    early
    0.63
    المكان
    0.62
     premat
    0.60
    Early
    0.57
    EARLY
    0.55
    Activations Density 0.479%

    No Known Activations