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. 6229
    Prev
    Next
    INDEX
    Explanations

    instances of the word "topic" and its variations

    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
    halb
    -0.68
    <h6>
    -0.67
    createServer
    -0.66
    StrictEqual
    -0.62
     sedentary
    -0.60
    Carthy
    -0.60
     Barrera
    -0.59
     Guimarães
    -0.59
     ?>">
    -0.58
    لمانيا
    -0.58
    POSITIVE LOGITS
     topic
    3.21
     topics
    3.08
     Topic
    2.97
     TOPIC
    2.79
    topic
    2.77
    Topic
    2.74
     Topics
    2.71
    Topics
    2.59
    topics
    2.56
    TOPIC
    2.49
    Activations Density 0.056%

    No Known Activations