© 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-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 8700
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hide" and variations related to visibility or display in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     differential
    -0.46
     exclusive
    -0.45
     inclusive
    -0.45
     Spri
    -0.44
     Fel
    -0.44
     fin
    -0.43
     drin
    -0.43
     Defend
    -0.43
     Hol
    -0.43
     perf
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.77
    styleType
    0.69
     autorytatywna
    0.69
     Wikimedijinoj
    0.65
    Vidite
    0.65
     övers
    0.64
    astéroïdes
    0.63
     فريبيس
    0.62
     Meksiku
    0.62
     चीज़ों
    0.62
    Activations Density 0.235%

    No Known Activations