Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 2919
    Prev
    Next
    INDEX
    Explanations

    references to cameras and microphones

    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
    Portale
    -0.72
    #
    -0.66
    Leif
    -0.66
    ruptcy
    -0.65
    %";
    -0.64
    GenerationType
    -0.64
    </tfoot>
    -0.64
     Leif
    -0.62
    +:+
    -0.59
    seamnă
    -0.59
    POSITIVE LOGITS
     cameras
    1.53
     Camer
    1.38
     camera
    1.37
    Cameras
    1.37
    Camera
    1.30
     Cameras
    1.30
     Camera
    1.30
     Camara
    1.27
    camera
    1.24
    kamer
    1.24
    Activations Density 0.073%

    No Known Activations