Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13274
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts between different concepts or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    simus
    -0.46
     JAXBElement
    -0.46
    jsonwebtoken
    -0.46
     mergeFrom
    -0.45
    EndGlobal
    -0.45
    TagHelper
    -0.45
     nga
    -0.43
    ורי
    -0.43
    RectangleBorder
    -0.43
     long
    -0.43
    POSITIVE LOGITS
     Another
    0.70
    Another
    0.69
     ANOTHER
    0.65
     similarly
    0.65
    OGND
    0.65
    another
    0.64
     تانيه
    0.64
     secondly
    0.64
     another
    0.63
    同じく
    0.63
    Activations Density 0.455%

    No Known Activations