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. 20-GEMMASCOPE-RES-16K
    6. 2379
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of infinity

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

    Tokens after "infinite"

    np_acts-logits-general · gemini-2.0-flash

    infinite or infinity contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.59
    tagHelper
    -0.58
    écial
    -0.57
    <h4>
    -0.54
    #+#
    -0.53
    PageRoute
    -0.53
     AspNetCore
    -0.50
    setVerticalGroup
    -0.50
     Процитовано
    -0.49
    inflater
    -0.48
    POSITIVE LOGITS
    ♾
    0.75
    CloseOperation
    0.66
    ]--;
    0.65
    nologies
    0.61
    sior
    0.60
    yntaxException
    0.59
     Possibilities
    0.58
    ∞
    0.58
    urably
    0.58
    VersionUID
    0.57
    Activations Density 0.148%

    No Known Activations