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. 0-GEMMASCOPE-RES-16K
    6. 7905
    Prev
    Next
    INDEX
    Explanations

    instances of user interface controls in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GraphicsUnit
    -0.71
    +#+
    -0.70
     onPostExecute
    -0.69
    URLException
    -0.65
    HMIS
    -0.64
     Buna
    -0.62
    brainly
    -0.62
    verifyException
    -0.59
    queryInterface
    -0.59
    NoSuchAlgorithm
    -0.59
    POSITIVE LOGITS
    Control
    1.84
     Control
    1.82
     control
    1.70
     CONTROL
    1.61
    CONTROL
    1.52
    control
    1.51
    ctrl
    1.33
    Ctrl
    1.32
     controlling
    1.23
     Controls
    1.22
    Activations Density 0.188%

    No Known Activations