© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 9526
    Prev
    Next
    INDEX
    Explanations

    instances of admitting or acknowledging wrongdoing or truth

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

    "admitted" or its variations

    np_acts-logits-general · gemini-2.0-flash

    admitting that or to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    STO
    -0.57
    άζ
    -0.56
    TIT
    -0.54
    mute
    -0.53
    iecie
    -0.52
    ext
    -0.51
     Ta
    -0.50
    gebracht
    -0.50
     Dra
    -0.50
    AccessorTable
    -0.50
    POSITIVE LOGITS
     Admit
    1.39
     admit
    1.38
     admits
    1.37
     admitted
    1.24
     admitting
    1.22
     admissions
    1.20
     Admissions
    1.15
    Admissions
    1.09
     confesses
    1.09
     confessed
    1.07
    Activations Density 0.093%

    No Known Activations