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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 6-GEMMASCOPE-RES-16K
    6. 3596
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to data and AJAX functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -1.41
    expandindo
    -1.24
     Efq
    -1.17
     étoit
    -1.17
    featureID
    -1.15
     myſelf
    -1.15
     betweenstory
    -1.10
     feroit
    -1.09
     avoient
    -1.06
    AsUp
    -1.06
    POSITIVE LOGITS
    -
    0.71
    –
    0.60
     initial
    0.58
     
    0.57
    <strong>
    0.57
     original
    0.56
     c
    0.56
    <em>
    0.55
     –
    0.54
    …
    0.52
    Activations Density 0.038%

    No Known Activations