© 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. 8-GEMMASCOPE-RES-16K
    6. 13710
    Prev
    Next
    INDEX
    Explanations

    elements and nodes in a data structure or algorithm context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -1.01
    AsUp
    -0.89
     propOrder
    -0.89
     للمعارف
    -0.86
     endblock
    -0.85
    setVerticalGroup
    -0.85
     defaultstate
    -0.84
     nakalista
    -0.84
     NSCoder
    -0.82
    AntiForgeryToken
    -0.82
    POSITIVE LOGITS
    1
    0.83
    2
    0.81
     
    0.74
    3
    0.69
     $
    0.65
    9
    0.59
    8
    0.58
    iParam
    0.58
    5
    0.57
     steg
    0.57
    Activations Density 0.560%

    No Known Activations