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. 24-GEMMASCOPE-RES-16K
    6. 4372
    Prev
    Next
    INDEX
    Explanations

    action and variations of the verb "play."

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

    "play" and its variations

    np_acts-logits-general · gemini-2.0-flash

    playing games or roles

    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
    XmlAccessorType
    -0.78
    EDEFAULT
    -0.69
    IonicModule
    -0.61
    onsored
    -0.60
    fromCharCode
    -0.59
     للمعارف
    -0.58
    KommentareTeilen
    -0.58
    resave
    -0.57
    featureID
    -0.57
    Попис
    -0.57
    POSITIVE LOGITS
     catch
    0.74
     coy
    0.67
     host
    0.66
     guitar
    0.65
     havoc
    0.65
     ball
    0.64
     golf
    0.62
    possum
    0.59
     poss
    0.58
    catch
    0.58
    Activations Density 0.058%

    No Known Activations