© 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. 15-GEMMASCOPE-RES-16K
    11. 8968
    Prev
    Next
    INDEX
    Explanations

    references to journal articles and academic publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.48
    VersionUID
    -0.47
     gev
    -0.41
    DockStyle
    -0.41
    ngdoc
    -0.40
    regado
    -0.40
    anguardia
    -0.40
    gridx
    -0.38
    itatis
    -0.38
    EClass
    -0.38
    POSITIVE LOGITS
    WebVitals
    0.70
     مرئيه
    0.66
    руппа
    0.61
    Vidite
    0.59
    出版年
    0.59
     boycott
    0.59
     disambiguazione
    0.59
    ]=>
    0.58
    ebrow
    0.58
    berdayakan
    0.58
    Activations Density 0.122%

    No Known Activations