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. 12-GEMMASCOPE-RES-16K
    6. 6491
    Prev
    Next
    INDEX
    Explanations

    terms related to combating terrorism and associated collaborations

    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
    ente
    -0.45
     unlike
    -0.45
     Theore
    -0.43
     felicità
    -0.43
     ki
    -0.42
     einge
    -0.42
     incendio
    -0.41
    è
    -0.41
    da
    -0.40
     alegria
    -0.40
    POSITIVE LOGITS
    InputTagHelper
    0.77
    Carriera
    0.74
     متعلقه
    0.74
    HasForeignKey
    0.73
    rrggbb
    0.73
     initiatives
    0.72
    principalTable
    0.72
     nahilalakip
    0.70
     synergies
    0.70
    csolódó
    0.70
    Activations Density 0.260%

    No Known Activations