© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 6872
    Prev
    Next
    INDEX
    Explanations

    references to positions, roles, or titles in a sporting context

    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
    bkz
    -0.42
     enrol
    -0.42
    Dichlor
    -0.42
    JsonKey
    -0.41
    sizable
    -0.41
    KJV
    -0.40
     too
    -0.39
    gridx
    -0.38
    atype
    -0.38
    Fancy
    -0.38
    POSITIVE LOGITS
    Personendaten
    0.86
    AndEndTag
    0.83
     <>",
    0.77
    CloseOperation
    0.75
    AddTagHelper
    0.75
    OGND
    0.74
     betweenstory
    0.74
    PerformLayout
    0.74
     NUKAT
    0.69
     ProtoMessage
    0.69
    Activations Density 0.221%

    No Known Activations