© 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. 18-GEMMASCOPE-RES-16K
    11. 8798
    Prev
    Next
    INDEX
    Explanations

    incidents involving law enforcement actions

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

    Follows "was" or describes people

    np_acts-logits-general · gemini-2.0-flash

    past actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enumi
    -0.79
    ftagPool
    -0.73
    providedIn
    -0.62
     nahilalakip
    -0.62
    ReusableCell
    -0.61
     CreateTagHelper
    -0.58
    featureID
    -0.58
     przecież
    -0.57
     Савезне
    -0.56
    +#+#
    -0.56
    POSITIVE LOGITS
     reportedly
    0.64
    />,
    0.62
     occupants
    0.62
     residents
    0.61
     southbound
    0.59
     northbound
    0.59
     juveniles
    0.58
    /-/
    0.58
    Бахар
    0.57
     identified
    0.57
    Activations Density 0.301%

    No Known Activations