© 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. 4-GEMMASCOPE-RES-16K
    6. 9915
    Prev
    Next
    INDEX
    Explanations

    references to services provided in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arşivlendi
    -0.72
    reactstrap
    -0.71
     Puig
    -0.65
    Oat
    -0.65
     Quell
    -0.65
     Wachs
    -0.63
     AGU
    -0.62
     Loth
    -0.62
    ggt
    -0.61
    ntö
    -0.60
    POSITIVE LOGITS
     services
    2.45
     Services
    2.24
    Services
    2.14
    services
    2.04
     SERVICES
    2.03
    SERVICES
    1.88
    ervices
    1.78
     diensten
    1.59
     servicios
    1.48
     serviços
    1.39
    Activations Density 0.108%

    No Known Activations