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. 3-GEMMASCOPE-RES-16K
    6. 10244
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "Control" and related variations in reference to user interface elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.82
     JSONException
    -0.79
    gdx
    -0.77
     Magee
    -0.71
     يتيمه
    -0.70
    NullException
    -0.70
    reness
    -0.70
     otomatig
    -0.69
    ponses
    -0.68
    脚注の使い方
    -0.68
    POSITIVE LOGITS
    Control
    1.52
     Control
    1.34
    control
    1.29
    CONTROL
    1.28
     CONTROL
    1.18
    ctrl
    1.11
     control
    1.11
    Ctrl
    1.10
    ctl
    1.04
     Controls
    0.99
    Activations Density 0.068%

    No Known Activations