© 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. 10-GEMMASCOPE-RES-16K
    11. 15932
    Prev
    Next
    INDEX
    Explanations

    terms related to both locations and transitions within contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.54
     Оно
    -0.52
    ธี
    -0.45
     оригіналу
    -0.44
    Enqueue
    -0.42
     FetchType
    -0.42
     deserved
    -0.42
    BarItem
    -0.41
    索
    -0.41
     enqueue
    -0.41
    POSITIVE LOGITS
    WriteBarrier
    0.78
    IsMutable
    0.75
    dicionado
    0.74
    SizeMode
    0.70
    InputBorder
    0.68
    Tembelea
    0.68
     Chwiliwch
    0.67
    fritt
    0.65
     Constructs
    0.64
    vantaged
    0.64
    Activations Density 0.759%

    No Known Activations