© 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. 12246
    Prev
    Next
    INDEX
    Explanations

    references to multi-faceted or multi-component strategies and systems

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

    "Multi" prefix

    np_acts-logits-general · gemini-2.0-flash

    multi-combination words

    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
    complexType
    -0.63
     "..\..\..\
    -0.60
     préférence
    -0.58
    FormTagHelper
    -0.57
     AssemblyCompany
    -0.55
    onAdd
    -0.55
    #+#
    -0.54
    ToListAsync
    -0.53
     "..\..\
    -0.52
    mtrl
    -0.52
    POSITIVE LOGITS
    tude
    0.69
    dimensional
    0.67
    purpose
    0.64
     purpose
    0.64
    tudes
    0.63
    layered
    0.61
    disciplinary
    0.60
    threading
    0.59
     lingual
    0.58
    coloured
    0.57
    Activations Density 0.088%

    No Known Activations