© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4246
    Prev
    Next
    INDEX
    Explanations

    terms related to permissions and regulations in legal and software contexts

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

    "Provided" or "subject to" clauses

    np_acts-logits-general · gemini-2.0-flash

    provided, subject to conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🙁
    -0.58
    ürtel
    -0.56
     HttpNotFound
    -0.55
    ☹
    -0.53
    脚注の使い方
    -0.52
     isComment
    -0.51
    urlpatterns
    -0.51
     onOptions
    -0.50
    {§
    -0.50
    ChildScrollView
    -0.49
    POSITIVE LOGITS
     provided
    2.60
     Provided
    2.34
    provided
    2.32
    Provided
    2.17
     PROVIDED
    2.09
     providing
    1.44
    PROVID
    1.42
    providing
    1.41
    Providing
    1.32
     subject
    1.32
    Activations Density 0.589%

    No Known Activations