© 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. 11-GEMMASCOPE-RES-16K
    11. 13488
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to web development and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    틴
    -0.41
    ,
    -0.40
     verticale
    -0.37
     ngang
    -0.37
     Google
    -0.36
    Hazard
    -0.36
    .
    -0.36
    cassert
    -0.36
     paraf
    -0.36
    hamshire
    -0.35
    POSITIVE LOGITS
    principalTable
    1.10
    InjectAttribute
    1.08
     contextLoads
    0.98
    DockStyle
    0.94
    rungsseite
    0.92
     AssemblyTitle
    0.90
    AnchorStyles
    0.90
     الحره
    0.88
    GEBURTSDATUM
    0.85
    bootstrapcdn
    0.83
    Activations Density 0.032%

    No Known Activations