© 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. 4570
    Prev
    Next
    INDEX
    Explanations

    words related to actions or traits involving manipulation and positioning

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

    before "ed" or "ing" suffixes

    np_acts-logits-general · gemini-2.0-flash

    word stems followed by common endings

    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
    ்கள்
    -0.74
    zzleHttp
    -0.67
    DispatchToProps
    -0.62
    AddWithValue
    -0.62
    ganie
    -0.60
    DrawerToggle
    -0.60
    operatives
    -0.60
    ிகள்
    -0.59
    AreEqual
    -0.59
    க்கும்
    -0.57
    POSITIVE LOGITS
    ing
    0.92
    ed
    0.81
    ings
    0.77
    expandindo
    0.72
    ment
    0.69
     متعلقه
    0.69
    able
    0.68
    ingly
    0.65
    ########.
    0.63
    存于互联网档案馆
    0.62
    Activations Density 0.357%

    No Known Activations