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. 6439
    Prev
    Next
    INDEX
    Explanations

    elements related to research, development, and inquiry in scientific and creative contexts

    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
     and
    -0.88
     gyhoeddwyd
    -0.65
     or
    -0.64
    rungsseite
    -0.60
    性和
    -0.59
    Климат
    -0.57
    __*/
    -0.56
    IGraphics
    -0.53
     يتيمه
    -0.53
    الإنجليزية
    -0.52
    POSITIVE LOGITS
     alike
    1.11
     whatnot
    0.72
     दोनों
    0.66
    virons
    0.60
     lainnya
    0.59
     invokingState
    0.56
     같은
    0.56
     LoginComponent
    0.56
    Etc
    0.55
     nữa
    0.55
    Activations Density 1.369%

    No Known Activations