© 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. 14-GEMMASCOPE-RES-16K
    6. 13098
    Prev
    Next
    INDEX
    Explanations

    informal expressions of personal opinions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Мексичка
    -1.00
     INTERESAR
    -0.99
    Portale
    -0.98
    GEBURTSDATUM
    -0.97
    InstrumentedTest
    -0.96
    ^(@)
    -0.92
    VERTISEMENT
    -0.89
    BibitemShut
    -0.87
    原始内容存档于
    -0.85
    — 
    -0.85
    POSITIVE LOGITS
    I
    0.95
     I
    0.90
    i
    0.73
    @
    0.68
    ma
    0.65
    ↵
    0.63
     i
    0.60
    1
    0.60
    The
    0.59
    hi
    0.59
    Activations Density 0.469%

    No Known Activations