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. 23-GEMMASCOPE-RES-16K
    6. 12384
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific methods or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RIPRODUZIONE
    -0.59
     ་་
    -0.52
    minWidth
    -0.52
     يتيمه
    -0.52
     pinulongan
    -0.50
    charCodeAt
    -0.49
    ;
    -0.48
    ɵɵelementStart
    -0.48
    MENAFN
    -0.47
     MERCHANTABILITY
    -0.46
    POSITIVE LOGITS
     she
    1.12
     her
    1.00
     he
    0.86
    ViewImports
    0.86
     him
    0.84
    she
    0.83
     Mr
    0.83
     his
    0.78
     그녀
    0.77
     Ms
    0.75
    Activations Density 3.089%

    No Known Activations