© 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. 21-GEMMASCOPE-RES-16K
    6. 13146
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Grand" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <=",
    -0.63
    queryInterface
    -0.61
     resourceCulture
    -0.59
    oredCriteria
    -0.58
    accro
    -0.54
    ToTensor
    -0.53
     situazione
    -0.52
     tartalomajánló
    -0.52
    verwijspagina
    -0.52
    uttori
    -0.51
    POSITIVE LOGITS
     grand
    0.83
     GRAND
    0.81
     Grand
    0.80
    GRAND
    0.76
    grand
    0.73
    Grand
    0.73
    iose
    0.68
     jury
    0.66
    daddy
    0.66
     slam
    0.65
    Activations Density 0.045%

    No Known Activations