© 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. 22-GEMMASCOPE-RES-16K
    11. 15385
    Prev
    Next
    INDEX
    Explanations

    details related to medical companies and their announcements

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

    "press", "media", or "legal"

    np_acts-logits-general · gemini-2.0-flash

    press release

    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
    HomeAsUpEnabled
    -0.51
    <bos>
    -0.47
     RECOMEND
    -0.45
    tableFuture
    -0.45
    HideFlags
    -0.44
    typeorm
    -0.42
    UObject
    -0.42
     henvisninger
    -0.42
     recommande
    -0.41
     arkadaş
    -0.41
    POSITIVE LOGITS
     press
    1.93
     Press
    1.71
     PRESS
    1.62
    press
    1.60
     media
    1.60
    Press
    1.59
     presse
    1.52
     Presse
    1.49
     PR
    1.46
    Media
    1.45
    Activations Density 0.163%

    No Known Activations