© 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. 8-GEMMASCOPE-RES-16K
    11. 4327
    Prev
    Next
    INDEX
    Explanations

    technical terms related to user interface components and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ніципа
    -0.66
     acorns
    -0.56
     yoox
    -0.52
     raisins
    -0.50
     față
    -0.48
    OfDay
    -0.48
     vorkommen
    -0.48
     Fifty
    -0.47
     Apare
    -0.47
     weights
    -0.47
    POSITIVE LOGITS
    TabIndex
    6.84
    ScopeManager
    1.17
     CreateTagHelper
    1.13
    DockStyle
    1.12
    AndEndTag
    1.12
    脚注の使い方
    1.11
     consultato
    1.09
    UseVisualStyle
    1.08
     AssemblyTitle
    1.08
     InputDecoration
    0.99
    Activations Density 0.003%

    No Known Activations