© 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. 24-GEMMASCOPE-RES-16K
    6. 16047
    Prev
    Next
    INDEX
    Explanations

    references to public health issues and discussions

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

    Code, health, or security contexts related to "public"

    np_acts-logits-general · gemini-2.0-flash

    public defender, public health, public keys

    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
     kaarangay
    -0.84
    Hochspringen
    -0.82
    mergeFrom
    -0.71
    ValueStyle
    -0.71
    AccessorTable
    -0.70
    @[+][
    -0.69
     tartalomajánló
    -0.67
    prime
    -0.67
    fromnode
    -0.66
    Enllaces
    -0.64
    POSITIVE LOGITS
    ally
    0.81
     sector
    0.77
     domain
    0.71
     servants
    0.65
    sector
    0.64
     opinion
    0.63
     Sector
    0.62
    domain
    0.62
     relations
    0.61
     health
    0.58
    Activations Density 0.063%

    No Known Activations