© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8387
    Prev
    Next
    INDEX
    Explanations

    code segments related to data processing in web applications

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

    Code related to services or data access

    np_acts-logits-general · gemini-2.0-flash

    JpaRepository and service usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uintptr
    -0.76
    ########.
    -0.67
     NgModule
    -0.66
    Jeografia
    -0.66
    出版年
    -0.64
    figsize
    -0.62
    Gambas
    -0.62
    IsPostBack
    -0.61
    Референце
    -0.60
    verwijspagina
    -0.60
    POSITIVE LOGITS
     service
    0.85
    service
    0.82
     services
    0.79
    Service
    0.76
     dao
    0.73
    services
    0.70
     서비스
    0.67
    OrderService
    0.67
    dao
    0.66
    svc
    0.66
    Activations Density 0.265%

    No Known Activations