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. 14-GEMMASCOPE-RES-16K
    6. 69
    Prev
    Next
    INDEX
    Explanations

    references to source code or source files

    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
     Tif
    -0.90
     <>",
    -0.81
     flocc
    -0.78
    ButterKnife
    -0.77
    aclk
    -0.75
    nastics
    -0.73
    Chim
    -0.69
    shadowRadius
    -0.69
    SBATCH
    -0.69
    Autoritní
    -0.69
    POSITIVE LOGITS
     SOURCE
    1.67
     source
    1.66
     Source
    1.56
     sources
    1.51
    Source
    1.46
    setSource
    1.40
    ource
    1.38
    source
    1.38
     Sources
    1.36
    sources
    1.30
    Activations Density 0.064%

    No Known Activations