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. 4-GEMMASCOPE-RES-16K
    6. 3538
    Prev
    Next
    INDEX
    Explanations

    the use of prepositions and their relationships in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.49
    htar
    -0.48
     heard
    -0.48
    不成
    -0.48
     chimiques
    -0.45
    stron
    -0.45
     fases
    -0.44
    -0.44
     loi
    -0.44
    nan
    -0.44
    POSITIVE LOGITS
     InputDecoration
    0.77
    DockStyle
    0.69
     cherchés
    0.69
    styleType
    0.67
    GoogleApiClient
    0.66
    felves
    0.66
     BoxDecoration
    0.65
    AnchorStyles
    0.65
     EconPapers
    0.65
    queryInterface
    0.65
    Activations Density 1.051%

    No Known Activations