© 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. 6982
    Prev
    Next
    INDEX
    Explanations

    elements related to deception and manipulation

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

    Two or three letter prefixes

    np_acts-logits-general · gemini-2.0-flash

    combining prefixes with suffixes

    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
    .
    -0.71
    ,
    -0.65
    ⓘ
    -0.64
    ↵↵
    -0.62
    ↵
    -0.58
    ↵↵↵
    -0.57
    :
    -0.56
    以外
    -0.55
     juvenil
    -0.55
     (
    -0.53
    POSITIVE LOGITS
    éphane
    0.76
    ésult
    0.74
    ientras
    0.73
    ſem
    0.73
    arangay
    0.72
    ugeot
    0.72
    ſſer
    0.72
    ratulations
    0.71
    ulongan
    0.71
    IBLIO
    0.71
    Activations Density 0.979%

    No Known Activations