© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 611
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "block" and related diagrammatic references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.78
    ükemmel
    -0.74
    =$?
    -0.74
     Ory
    -0.73
     couverte
    -0.73
    HttpFoundation
    -0.71
     RNN
    -0.70
     CPE
    -0.69
    stdarg
    -0.69
     للاسماء
    -0.68
    POSITIVE LOGITS
     block
    3.44
     Block
    3.27
     blocks
    3.25
    block
    3.20
     BLOCK
    3.17
    Block
    3.05
     Blocks
    3.00
    BLOCK
    2.93
    blocks
    2.88
    Blocks
    2.68
    Activations Density 0.060%

    No Known Activations