© 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. 5931
    Prev
    Next
    INDEX
    Explanations

    expressions indicating perception or visibility

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

    "[Verb] + as" construction

    np_acts-logits-general · gemini-2.0-flash

    not seen or desired

    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
    立
    -0.61
    ys
    -0.59
    y
    -0.59
    сте
    -0.57
    h
    -0.55
    K
    -0.54
    (
    -0.53
    dl
    -0.51
    2
    -0.51
    c
    -0.51
    POSITIVE LOGITS
     >=",
    1.04
    tvguidetime
    0.90
     photolibrary
    0.84
    ruptedException
    0.83
    MessageState
    0.83
    EDEFAULT
    0.82
    DebuggerNonUser
    0.78
     HasFactory
    0.78
    ագրություններ
    0.77
    Ecotoxicity
    0.77
    Activations Density 0.354%

    No Known Activations