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. 7-GEMMASCOPE-RES-16K
    6. 6255
    Prev
    Next
    INDEX
    Explanations

    references to potential military conflicts and geopolitical tensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bem
    -0.46
    Prior
    -0.44
    advanced
    -0.43
    ArgsConstructor
    -0.42
    Bul
    -0.42
     spheres
    -0.42
     Bul
    -0.42
     tiros
    -0.41
     Previously
    -0.40
    previously
    -0.40
    POSITIVE LOGITS
    StoryboardSegue
    0.90
    DockStyle
    0.90
    principalTable
    0.84
    AddTagHelper
    0.83
     EconPapers
    0.77
     يتيمه
    0.73
     通販
    0.68
    archiviato
    0.67
    ValueStyle
    0.67
     MainAxisSize
    0.66
    Activations Density 0.525%

    No Known Activations