© 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. 24-GEMMASCOPE-RES-16K
    11. 14357
    Prev
    Next
    INDEX
    Explanations

    keywords related to medical treatment, particularly concerning addiction recovery and prescriptions

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

    Describes a transition or change

    np_acts-logits-general · gemini-2.0-flash

    migration and switching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onViewCreated
    -0.61
    وام
    -0.54
     BeautifulSoup
    -0.54
    ToBounds
    -0.54
     riemp
    -0.54
    tagHelperRunner
    -0.53
    OrNil
    -0.49
     raffredd
    -0.49
     mattino
    -0.49
     ricev
    -0.48
    POSITIVE LOGITS
     transition
    2.94
     switch
    2.63
     transitioning
    2.56
     Transition
    2.54
     switching
    2.52
    transition
    2.46
     transitions
    2.46
    Transition
    2.41
     transitioned
    2.39
     Switching
    2.28
    Activations Density 0.657%

    No Known Activations