© 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. 22-GEMMASCOPE-RES-16K
    11. 10837
    Prev
    Next
    INDEX
    Explanations

    the use of angle brackets and parentheses in code elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets with generics

    np_acts-logits-general · gemini-2.0-flash

    JAVA generic types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.71
     he
    -0.67
    ,
    -0.65
     so
    -0.64
     to
    -0.61
     "
    -0.60
     is
    -0.60
     O
    -0.59
    .
    -0.58
     The
    -0.58
    POSITIVE LOGITS
     myſelf
    1.31
     poffible
    1.17
     itſelf
    1.13
     purpoſe
    1.11
     themſelves
    1.10
     Monfieur
    1.09
     Houſe
    1.08
     ſtate
    1.08
     reaſon
    1.05
     pleaſure
    1.05
    Activations Density 0.035%

    No Known Activations