© 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-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8357
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rather" indicating preference or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ToBounds
    -0.74
     uuidv
    -0.74
     Tacitus
    -0.65
    labelledby
    -0.65
     Lue
    -0.65
     Oswald
    -0.64
     Gunn
    -0.63
    illotine
    -0.63
    ظيم
    -0.63
     Ennis
    -0.63
    POSITIVE LOGITS
    uttosto
    1.03
     Rather
    0.90
    Rather
    0.85
    rather
    0.76
     rather
    0.76
     than
    0.74
    Vrij
    0.71
     Fairly
    0.71
     vort
    0.70
     quite
    0.68
    Activations Density 0.036%

    No Known Activations