© 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. 24-GEMMASCOPE-RES-16K
    11. 12172
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to installation or technical instructions

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

    Tokens before capitalized words in French text

    np_acts-logits-general · gemini-2.0-flash

    French words ending in "er" or "re"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GOTREF
    -0.67
    AutoField
    -0.64
    PyExc
    -0.64
    ])));
    -0.61
     Numerade
    -0.60
    География
    -0.60
     NUKAT
    -0.59
     typelib
    -0.59
     mustard
    -0.58
    principalColumn
    -0.57
    POSITIVE LOGITS
    IActionResult
    0.49
    col
    0.48
     Inventors
    0.47
    ClassPath
    0.47
    double
    0.45
    nock
    0.45
    Double
    0.45
     living
    0.45
    chet
    0.44
    pose
    0.43
    Activations Density 0.134%

    No Known Activations