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. 17-GEMMASCOPE-RES-16K
    6. 5820
    Prev
    Next
    INDEX
    Explanations

    references to the concept of creating space or room for ideas, thoughts, or opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeConstraints
    -0.80
     AssemblyCulture
    -0.68
    Παραπομπές
    -0.67
    contentLoaded
    -0.66
    ֹא
    -0.57
    enderror
    -0.57
    Contours
    -0.55
    &__
    -0.55
    aarrggbb
    -0.54
    ("'"
    -0.54
    POSITIVE LOGITS
     space
    1.23
     room
    0.99
     allowance
    0.99
     espaço
    0.97
    Space
    0.96
     espacio
    0.95
     hueco
    0.94
     ruimte
    0.93
     spazio
    0.93
    space
    0.92
    Activations Density 0.192%

    No Known Activations