© 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. 18-GEMMASCOPE-RES-16K
    11. 228
    Prev
    Next
    INDEX
    Explanations

    words related to characteristics of entities such as "identifiable," "actionable," and "adjustable."

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

    ending in "able", "ible", or "izable"

    np_acts-logits-general · gemini-2.0-flash

    identifiable, -able, -ible suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    -0.84
    n
    -0.68
    es
    -0.68
    jspx
    -0.59
    ة
    -0.57
    re
    -0.56
    m
    -0.56
    сомо
    -0.55
    RepeatedField
    -0.55
    en
    -0.54
    POSITIVE LOGITS
     Theſe
    0.94
    ABLE
    0.91
    chable
    0.91
    gable
    0.88
     Touchable
    0.87
    izable
    0.86
     Efq
    0.85
    vable
    0.85
    tvguidetime
    0.83
    able
    0.83
    Activations Density 0.256%

    No Known Activations