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. 4-GEMMASCOPE-RES-16K
    6. 15980
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to photography, specifically focusing mechanisms and settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queryInterface
    -0.53
    éo
    -0.47
    зна
    -0.47
    Inflater
    -0.46
     estimés
    -0.45
     oto
    -0.44
    Wrap
    -0.42
     Radon
    -0.41
     antioxidants
    -0.41
    áklad
    -0.41
    POSITIVE LOGITS
     Roskov
    0.78
    MLLoader
    0.66
    .*")]
    0.65
    __*/
    0.62
    makeConstraints
    0.62
     GenerationType
    0.61
    Focusing
    0.61
     "..\..\
    0.59
     lens
    0.58
     "..\..\..\
    0.58
    Activations Density 0.682%

    No Known Activations