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. 12-GEMMASCOPE-RES-16K
    6. 3164
    Prev
    Next
    INDEX
    Explanations

    phrases related to quantity and sufficiency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Климат
    -0.53
    RenderAtEndOf
    -0.48
    cillas
    -0.47
    azine
    -0.47
     apk
    -0.47
     يتيمه
    -0.46
    enido
    -0.46
    trui
    -0.46
    ejb
    -0.46
    Panamoan
    -0.45
    POSITIVE LOGITS
    AddTagHelper
    0.78
    ValueStyle
    0.62
    awtextra
    0.59
     disambiguazione
    0.59
    lindungan
    0.54
    lwjgl
    0.53
     istore
    0.52
    プーン
    0.52
    脚注の使い方
    0.51
     NSCoder
    0.51
    Activations Density 0.685%

    No Known Activations