© 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-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 9868
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "return" and its variations, indicating a focus on the concept of coming back or returning from a place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
    SharedCtor
    -0.40
     confé
    -0.39
    mousedown
    -0.38
    almi
    -0.38
     apret
    -0.37
     étag
    -0.36
     ministres
    -0.36
     médié
    -0.36
     doute
    -0.36
     procedimientos
    -0.36
    POSITIVE LOGITS
     returning
    1.17
     Returning
    1.16
     returned
    1.14
     return
    1.11
     Returned
    1.09
    Returning
    1.07
    returning
    1.04
     Return
    1.02
     RETURN
    1.01
    returned
    1.00
    Activations Density 0.217%

    No Known Activations