Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 2054
    Prev
    Next
    INDEX
    Explanations

    technical terminology and numerical data related to scientific studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.62
    makeText
    -0.54
    JspWriter
    -0.53
    AndEndTag
    -0.51
     وتسجيلات
    -0.50
    CppCodeGen
    -0.49
     Manley
    -0.47
     AttributeSet
    -0.46
     createStore
    -0.46
    orex
    -0.46
    POSITIVE LOGITS
     SB
    1.21
    SB
    1.16
     RB
    1.12
     WB
    1.11
     HB
    1.10
    VB
    1.09
    RB
    1.08
     LB
    1.08
     PB
    1.08
     AB
    1.08
    Activations Density 0.442%

    No Known Activations