© 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. 2-GEMMASCOPE-RES-16K
    6. 3351
    Prev
    Next
    INDEX
    Explanations

    different methods or approaches to understanding concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxDecoration
    -0.60
    irmish
    -0.59
    oredCriteria
    -0.57
    Спољашње
    -0.52
     volume
    -0.50
    Referencie
    -0.50
    Ữ
    -0.48
    ReusableCell
    -0.48
     müsste
    -0.48
    stärke
    -0.47
    POSITIVE LOGITS
     ways
    3.03
     Ways
    2.73
     WAYS
    2.55
    Ways
    2.39
    ways
    1.87
    WAYS
    1.83
     maneras
    1.71
     maneiras
    1.58
     manières
    1.45
     façons
    1.27
    Activations Density 0.075%

    No Known Activations