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. 3-GEMMASCOPE-RES-16K
    6. 8944
    Prev
    Next
    INDEX
    Explanations

    references to services offered or provided

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reactstrap
    -0.66
    MigrationBuilder
    -0.60
     orar
    -0.59
    Šaltiniai
    -0.58
     Quell
    -0.57
    ggt
    -0.56
     étan
    -0.55
    Oat
    -0.54
    CompleteListener
    -0.53
     Doble
    -0.51
    POSITIVE LOGITS
     services
    2.88
     Services
    2.62
    Services
    2.50
     SERVICES
    2.41
    services
    2.41
    SERVICES
    2.20
    ervices
    2.06
     diensten
    1.86
     servicios
    1.81
     serviços
    1.67
    Activations Density 0.070%

    No Known Activations