© 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. 8-GEMMASCOPE-RES-16K
    6. 13684
    Prev
    Next
    INDEX
    Explanations

    references to organizations, species, and databases related to biodiversity and conservation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaiter
    -0.60
    verticalLayout
    -0.52
    emplare
    -0.51
     invokingState
    -0.50
    SerializedName
    -0.48
     sés
    -0.48
    ViewFeatures
    -0.46
    RATION
    -0.46
    TargetApi
    -0.46
    subfigure
    -0.46
    POSITIVE LOGITS
    enumii
    0.73
     itſelf
    0.63
     thousands
    0.60
    AddTagHelper
    0.60
    thousands
    0.59
     dozens
    0.59
    hundreds
    0.59
     hundreds
    0.58
     nationalities
    0.58
     Савезне
    0.57
    Activations Density 0.546%

    No Known Activations