© 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. 13832
    Prev
    Next
    INDEX
    Explanations

    instances of realization or awareness of important concepts or truths

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

    Tokens preceding "that" or related to "realize"

    np_acts-logits-general · gemini-2.0-flash

    realize that

    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
     الحره
    -0.58
     propOrder
    -0.54
     pinulongan
    -0.52
     SwitchCompat
    -0.45
    RTEX
    -0.44
     للمعارف
    -0.44
     besz
    -0.43
     ब्रेकडाउन
    -0.42
    tomation
    -0.40
    üyada
    -0.40
    POSITIVE LOGITS
     realise
    0.80
     realize
    0.77
     realisation
    0.76
     realises
    0.76
     realised
    0.76
     realizes
    0.75
     realized
    0.72
     realising
    0.72
     realization
    0.71
     realizing
    0.68
    Activations Density 0.281%

    No Known Activations