© 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. 20-GEMMASCOPE-RES-16K
    11. 2495
    Prev
    Next
    INDEX
    Explanations

    indicative markers or tags in structured data and documentation

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

    Followed by a capital letter

    np_acts-logits-general · gemini-2.0-flash

    renormalized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.72
    ]';
    -0.54
    />";
    -0.52
     “
    -0.52
     us
    -0.52
     me
    -0.51
     they
    -0.51
     stop
    -0.51
    +#+
    -0.51
     devoirs
    -0.49
    POSITIVE LOGITS
     poffible
    0.80
     myſelf
    0.78
     pleaſure
    0.77
     leſs
    0.73
     pixels
    0.72
     neceffary
    0.72
     ſtill
    0.70
     fevere
    0.70
     reaſon
    0.69
     ſmall
    0.67
    Activations Density 0.173%

    No Known Activations