© 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. 1922
    Prev
    Next
    INDEX
    Explanations

    statements about the necessity of support and contributions for success in programs or projects

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

    "without" or its translation

    np_acts-logits-general · gemini-2.0-flash

    [concept] without the necessity of

    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
     שוליים
    -0.53
    ETHOD
    -0.52
    Constantes
    -0.48
    roppo
    -0.47
    kso
    -0.47
    sprechend
    -0.46
    letoe
    -0.46
    oara
    -0.44
    роде
    -0.44
    OGEN
    -0.44
    POSITIVE LOGITS
     Without
    1.88
     without
    1.86
    Without
    1.83
    without
    1.71
    Ohne
    1.57
     Ohne
    1.54
     ohne
    1.47
     WITHOUT
    1.47
    WITHOUT
    1.47
     zonder
    1.44
    Activations Density 0.262%

    No Known Activations