© 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. 5635
    Prev
    Next
    INDEX
    Explanations

    proper nouns and character names

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

    Appears before a name or initial

    np_acts-logits-general · gemini-2.0-flash

    common first names

    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
    ın
    -0.49
    a
    -0.48
    on
    -0.48
    an
    -0.48
     (
    -0.47
    um
    -0.46
     
    -0.44
    sob
    -0.44
    m
    -0.43
    en
    -0.43
    POSITIVE LOGITS
     Monfieur
    1.16
     Efq
    1.14
     Jefus
    1.11
     Theſe
    1.07
     Shakspeare
    1.06
     raiſ
    1.05
     uſed
    1.05
     Houſe
    1.04
     houſe
    1.01
     himſelf
    1.01
    Activations Density 0.166%

    No Known Activations