Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 5657
    Prev
    Next
    INDEX
    Explanations

    specific programming or technical terminology related to functions and methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    necedor
    -1.02
    ocidad
    -0.86
    здрав
    -0.85
    hiculo
    -0.81
    cyklopedia
    -0.79
    tymologie
    -0.79
    достатки
    -0.78
    помним
    -0.76
    falen
    -0.76
    dasarkan
    -0.74
    POSITIVE LOGITS
    withstanding
    1.09
    foundland
    0.87
    которые
    0.83
    giveness
    0.77
    NUMX
    0.73
    itudinal
    0.72
    StreetMap
    0.71
    quakes
    0.69
    tagez
    0.68
    stalgia
    0.65
    Activations Density 0.572%

    No Known Activations