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. 24-GEMMASCOPE-RES-16K
    6. 8261
    Prev
    Next
    INDEX
    Explanations

    language associated with pleasure and the balance of cost versus benefit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "come" or its variations

    np_acts-logits-general · gemini-2.0-flash

    future to come

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.75
    findpost
    -0.61
    PDOException
    -0.58
    XmlAccessorType
    -0.55
    ējās
    -0.52
    AddHtmlAttribute
    -0.52
    NUMX
    -0.51
     <<<<<<<<<<<<<<
    -0.51
    RenderAtEndOf
    -0.49
    Continues
    -0.48
    POSITIVE LOGITS
     come
    3.43
     comes
    3.18
    come
    2.75
     Come
    2.75
     COME
    2.69
    Come
    2.68
    comes
    2.62
     came
    2.62
     Comes
    2.58
     COMES
    2.48
    Activations Density 0.491%

    No Known Activations