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. 10287
    Prev
    Next
    INDEX
    Explanations

    structured data and mathematical notation

    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
    ']}
    -0.70
    banez
    -0.69
     (
    -0.65
    ]</
    -0.64
     <
    -0.64
    [toxicity=0]
    -0.63
    e
    -0.62
     }}">
    -0.62
    ు
    -0.61
     -
    -0.58
    POSITIVE LOGITS
     Theſe
    1.55
     uſed
    1.45
     myſelf
    1.44
     Anſ
    1.41
     Monfieur
    1.40
     Reſ
    1.39
     raiſ
    1.38
     itſelf
    1.38
     Jefus
    1.37
     whoſe
    1.34
    Activations Density 0.614%

    No Known Activations