© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10869
    Prev
    Next
    INDEX
    Explanations

    words and phrases in a specific Indian language related to cultural and religious themes

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

    containing unusual characters/diacritics

    np_acts-logits-general · gemini-2.0-flash

    Schleswig-Holstein, schedule, balabanchilar

    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
    enumii
    -0.50
    </thead>
    -0.47
     mandatario
    -0.46
    blockList
    -0.44
    titleMargin
    -0.44
    uteen
    -0.43
    erover
    -0.43
    ђу
    -0.42
    ില
    -0.41
    multirow
    -0.41
    POSITIVE LOGITS
     invokingState
    0.68
    reportWebVitals
    0.67
    AutoScaleMode
    0.65
     jScrollPane
    0.64
     Normdatei
    0.63
    SQLiteDatabase
    0.62
    aarrggbb
    0.58
     uska
    0.57
    EReference
    0.57
    AnimationsModule
    0.57
    Activations Density 0.010%

    No Known Activations