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. 19-GEMMASCOPE-RES-16K
    6. 307
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terminology related to experiments and assays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]--;
    -0.76
    sizeCache
    -0.64
    LayoutConstraint
    -0.63
    </thead>
    -0.58
    ,:,
    -0.55
    DockStyle
    -0.53
    ="{{$
    -0.52
    /$',
    -0.51
    ')")
    -0.51
    transQ
    -0.51
    POSITIVE LOGITS
     with
    1.50
    with
    1.33
     containing
    1.22
     WITH
    1.15
     avec
    1.15
     accompanied
    1.15
    带有
    1.14
     featuring
    1.05
     inclusief
    1.03
    avec
    1.02
    Activations Density 0.877%

    No Known Activations