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. 5778
    Prev
    Next
    INDEX
    Explanations

    situations involving interpersonal conflict and emotional interactions

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

    followed by a comma

    np_acts-logits-general · gemini-2.0-flash

    watching and moving

    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
     in
    -0.50
    ųjų
    -0.43
    ByDefault
    -0.42
    ente
    -0.42
     we
    -0.42
     by
    -0.41
    env
    -0.41
    πέ
    -0.41
    ponen
    -0.40
    eben
    -0.40
    POSITIVE LOGITS
    verwijspagina
    0.89
     hoping
    0.88
     تانيه
    0.84
     causing
    0.83
     whereupon
    0.81
     unaware
    0.80
     oblivious
    0.79
     wondering
    0.78
     knowing
    0.78
    causing
    0.78
    Activations Density 0.243%

    No Known Activations