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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 3069
    Prev
    Next
    INDEX
    Explanations

    terms related to space and spatial constraints

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

    "space"

    np_acts-logits-general · gemini-2.0-flash

    space between, for, or constraints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.97
     Majefty
    -0.96
    OGND
    -0.96
     pleaſure
    -0.95
    ſelves
    -0.91
     >=",
    -0.87
     Wiktionnaire
    -0.86
     themſelves
    -0.86
    })*/
    -0.84
     ExecuteAsync
    -0.83
    POSITIVE LOGITS
     spaces
    1.42
     space
    1.42
     Space
    1.30
     SPACE
    1.30
    Spaces
    1.29
     Spaces
    1.24
    Space
    1.21
    spaces
    1.21
    space
    1.18
    SPACE
    1.15
    Activations Density 0.078%

    No Known Activations