© 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. 20-GEMMASCOPE-RES-16K
    6. 14308
    Prev
    Next
    INDEX
    Explanations

    references to the Achilles tendon and related anatomical aspects

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

    "Achilles" or names followed by tendon/tendinitis

    np_acts-logits-general · gemini-2.0-flash

    Achilles tendon

    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
    ing
    -3.08
    ING
    -2.23
    ة
    -1.15
    ging
    -1.13
    ی
    -1.11
    ingi
    -1.10
    izing
    -0.94
    ingar
    -0.93
    ning
    -0.91
    ingan
    -0.90
    POSITIVE LOGITS
     latter
    0.81
    ^(@)
    0.81
    🔥🔥
    0.81
    śmy
    0.74
    bladder
    0.72
    abinieri
    0.71
    ścioła
    0.68
     Theſe
    0.67
    ル
    0.66
    ist
    0.66
    Activations Density 0.873%

    No Known Activations