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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24-GEMMASCOPE-RES-16K
    6. 16354
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and documentation

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

    Followed by legal or business documents

    np_acts-logits-general · gemini-2.0-flash

    official documents and statements

    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
    الإنجليزية
    -0.54
    spaceBetween
    -0.54
     namorado
    -0.50
    yticks
    -0.48
     potrivit
    -0.48
     Krä
    -0.48
     taglio
    -0.47
    IUrlHelper
    -0.47
     raconter
    -0.46
     llorar
    -0.46
    POSITIVE LOGITS
     minutes
    1.04
     Minutes
    1.03
     memorandum
    0.95
    Minutes
    0.90
     letter
    0.89
    minutes
    0.89
     Memorandum
    0.87
     circular
    0.84
     memo
    0.83
     document
    0.81
    Activations Density 0.889%

    No Known Activations