© 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. 38-GEMMASCOPE-RES-16K
    6. 13743
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this" and related phrases denoting presence or immediacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     latter
    -0.42
     defaultstate
    -0.40
    NameInMap
    -0.38
     LATER
    -0.37
    Jîn
    -0.36
    +:+
    -0.35
     zost
    -0.34
     later
    -0.34
    GEBURTS
    -0.34
    liferay
    -0.34
    POSITIVE LOGITS
     morning
    0.80
     week
    0.78
     weekend
    0.78
     year
    0.75
     année
    0.73
     afternoon
    0.71
    morning
    0.69
     month
    0.68
     summer
    0.67
     mattina
    0.66
    Activations Density 0.217%

    No Known Activations