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. 1-GEMMASCOPE-RES-16K
    6. 6920
    Prev
    Next
    INDEX
    Explanations

    terms related to characteristics and qualities in artistic and technological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.76
    copg
    -0.73
     disambiguazione
    -0.70
    SequentialGroup
    -0.69
     propOrder
    -0.68
    enumi
    -0.67
    iarkan
    -0.63
    bootstrapcdn
    -0.62
     समीक्षाओं
    -0.62
    BatchNorm
    -0.61
    POSITIVE LOGITS
    ador
    0.55
    ativement
    0.55
     поли
    0.54
    ny
    0.51
    ца
    0.51
    urum
    0.50
     um
    0.48
    vaz
    0.48
    не
    0.48
     на
    0.48
    Activations Density 0.126%

    No Known Activations