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. 22-GEMMASCOPE-RES-16K
    6. 13813
    Prev
    Next
    INDEX
    Explanations

    terms associated with healthcare and chronic diseases

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

    followed by "an" or "ans"

    np_acts-logits-general · gemini-2.0-flash

    Christianity related word endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chengladbach
    -0.44
     Clyde
    -0.43
    ụng
    -0.41
     Hogarth
    -0.41
    сомо
    -0.41
    estina
    -0.40
    Clyde
    -0.40
    Emilio
    -0.40
     Kiy
    -0.39
     sos
    -0.39
    POSITIVE LOGITS
    ans
    1.17
    án
    1.08
    ANS
    1.04
    ann
    1.04
    AN
    1.02
    àn
    1.01
    aan
    0.99
    ANN
    0.95
    ana
    0.95
    ano
    0.94
    Activations Density 0.514%

    No Known Activations