Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 2838
    Prev
    Next
    INDEX
    Explanations

    elements related to technical processes or mechanical details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    is
    -0.66
    ang
    -0.65
    and
    -0.64
    io
    -0.63
    u
    -0.62
    to
    -0.61
    on
    -0.60
    …
    -0.58
     
    -0.58
    ...
    -0.56
    POSITIVE LOGITS
    setVerticalGroup
    1.33
    didSet
    1.01
    ".
    
    0.97
    ])));
    0.93
    '));
    
    0.92
     AssemblyCulture
    0.89
    "):
    
    0.88
    HomeAsUpEnabled
    0.88
     CreateTagHelper
    0.86
     insuffisamment
    0.84
    Activations Density 1.319%

    No Known Activations