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

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 808
    Prev
    Next
    INDEX
    Explanations

    phrases related to events and their timing

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

    "begin" or "early"

    np_acts-logits-general · gemini-2.0-flash

    early or premature action

    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
    richTextPanel
    -0.58
    bewerken
    -0.53
    Asts
    -0.52
     Reverso
    -0.51
    pulumi
    -0.50
    økt
    -0.50
    Portály
    -0.50
    Datuak
    -0.49
     pulumi
    -0.49
    exitRule
    -0.48
    POSITIVE LOGITS
     early
    1.12
     prematurely
    0.98
     premature
    0.98
    early
    0.94
    提前
    0.89
     EARLY
    0.89
     Early
    0.88
    Early
    0.88
     already
    0.86
     earlier
    0.82
    Activations Density 0.644%

    No Known Activations