© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 5765
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Dean" and related derivatives

    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
     AssemblyTitle
    -0.65
    ewski
    -0.63
    """
    -0.63
     Berman
    -0.62
    stwie
    -0.61
     Avo
    -0.60
    heu
    -0.59
    ///
    -0.59
     sien
    -0.58
    ombo
    -0.58
    POSITIVE LOGITS
     Dean
    1.79
     dean
    1.70
     DEAN
    1.63
    Dean
    1.62
    DEAN
    1.30
     Deans
    1.17
     Creatures
    1.13
    dean
    1.10
    creatures
    1.01
     creatures
    0.98
    Activations Density 0.055%

    No Known Activations