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. 12-GEMMASCOPE-RES-16K
    6. 5592
    Prev
    Next
    INDEX
    Explanations

    sections related to software testing and bug reporting procedures

    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
    OGND
    -0.86
    __*/
    -0.80
     محفوظة
    -0.76
     SwitchCompat
    -0.70
    ########.
    -0.69
     Walkover
    -0.68
     gede
    -0.68
     GenerationType
    -0.66
     оригіналу
    -0.65
     مرئيه
    -0.64
    POSITIVE LOGITS
    Acknowledgments
    0.49
    none
    0.48
    None
    0.47
     suom
    0.47
     none
    0.47
     namely
    0.45
     None
    0.44
    namely
    0.43
    NONE
    0.43
    —
    0.41
    Activations Density 0.660%

    No Known Activations