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. 24-GEMMASCOPE-RES-16K
    6. 15355
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly in the context of their careers and biographical details

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

    Precedes/follows information in parentheses

    np_acts-logits-general · gemini-2.0-flash

    names and dates followed by facts

    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
    المشاركات
    -0.70
    LikeLike
    -0.63
     instead
    -0.63
     CrossRef
    -0.62
    hdashline
    -0.60
    ThemeOverlay
    -0.56
    Климат
    -0.56
     then
    -0.55
    instead
    -0.55
     when
    -0.55
    POSITIVE LOGITS
     bezeichneter
    0.58
    ⓘ
    0.57
     المعيارى
    0.56
    KURZBESCHREIBUNG
    0.53
    OGND
    0.52
     disambiguazione
    0.52
     wła
    0.52
     professionally
    0.48
     pseudonym
    0.47
     död
    0.47
    Activations Density 0.430%

    No Known Activations