© 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. 10403
    Prev
    Next
    INDEX
    Explanations

    concepts and practices related to coding standards and conventions

    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
    Advanced
    -0.56
     advanced
    -0.55
     MessageBoxIcon
    -0.52
    advanced
    -0.51
     BoxFit
    -0.48
    ioutil
    -0.48
     hin
    -0.47
     facult
    -0.46
     Facult
    -0.46
    原始内容存档于
    -0.46
    POSITIVE LOGITS
     disambiguazione
    0.63
     pinulongan
    0.59
     corrispond
    0.57
    ]]]
    0.56
     règle
    0.56
    convention
    0.56
    awtextra
    0.56
     standaard
    0.55
     estándar
    0.55
     predictable
    0.54
    Activations Density 0.739%

    No Known Activations