© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8367
    Prev
    Next
    INDEX
    Explanations

    references to barriers or constraints, particularly fences and the concept of being forced

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.97
    AddTagHelper
    -0.93
    EndContext
    -0.89
     дописавши
    -0.89
    mybatisplus
    -0.82
    ImageContext
    -0.82
    StoryboardSegue
    -0.80
     EconPapers
    -0.78
     NSCoder
    -0.78
     المعيارى
    -0.77
    POSITIVE LOGITS
     forced
    0.67
     species
    0.55
    rag
    0.51
     degree
    0.51
    espèce
    0.51
     especies
    0.51
     series
    0.50
    iencia
    0.50
     similaires
    0.49
    ★★★★☆
    0.49
    Activations Density 0.100%

    No Known Activations