© 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. 10191
    Prev
    Next
    INDEX
    Explanations

    references to authority figures and their roles or statements

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

    Comes after a name or title

    np_acts-logits-general · gemini-2.0-flash

    names after commas

    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
    du
    -0.51
    PR
    -0.46
     z
    -0.46
    SC
    -0.45
     Hotspur
    -0.45
     PR
    -0.44
    java
    -0.44
    .
    -0.43
     ব
    -0.43
    pae
    -0.43
    POSITIVE LOGITS
     Monfieur
    1.09
    ########.
    1.03
     متعلقه
    1.02
     auffi
    1.02
    TagMode
    1.00
     iſt
    0.96
     Efq
    0.95
    ſelf
    0.95
    parsedMessage
    0.95
    #+#
    0.94
    Activations Density 0.714%

    No Known Activations