© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10561
    Prev
    Next
    INDEX
    Explanations

    words indicating a high frequency or abundance of something

    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
    5
    -0.83
    2
    -0.81
    7
    -0.79
    1
    -0.74
    3
    -0.74
    Clik
    -0.73
    4
    -0.70
    6
    -0.69
     Spri
    -0.66
    o
    -0.66
    POSITIVE LOGITS
     numerous
    1.95
     Numerous
    1.74
    Numerous
    1.69
    numer
    1.44
     numerosas
    1.41
     numerosos
    1.39
     numerose
    1.33
     numerosi
    1.31
     innumerable
    1.28
     countless
    1.27
    Activations Density 0.067%

    No Known Activations