© 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. 2122
    Prev
    Next
    INDEX
    Explanations

    terms related to database entity relationships

    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
    KommentareTeilen
    -0.63
     Grecs
    -0.59
    ього
    -0.58
    LookAnd
    -0.56
     normaux
    -0.55
    GraphicsUnit
    -0.55
    %)$
    -0.54
     internationaux
    -0.54
     mourut
    -0.52
     MainAxisSize
    -0.52
    POSITIVE LOGITS
     users
    0.91
     employee
    0.85
     user
    0.85
     Users
    0.83
     customer
    0.82
     User
    0.79
     student
    0.76
     customers
    0.73
     Customer
    0.71
     Employee
    0.68
    Activations Density 0.469%

    No Known Activations