© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 4054
    Prev
    Next
    INDEX
    Explanations

    concepts related to technical procedures and measurements

    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
    __':
    
    -0.99
     ―――――
    -0.81
    .)}
    -0.80
    \<^
    -0.80
    "]="
    -0.79
    "](
    -0.79
     autorytatywna
    -0.79
    "]:
    -0.78
    %");
    -0.77
    Tikang
    -0.77
    POSITIVE LOGITS
     =
    0.61
    '
    0.59
     olarak
    0.58
    <eos>
    0.58
     stesso
    0.57
    的
    0.56
     sendiri
    0.56
    ...
    0.56
     of
    0.56
     from
    0.53
    Activations Density 18.981%

    No Known Activations