© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9797
    Prev
    Next
    INDEX
    Explanations

    references and citations in academic texts

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

    Text between brackets or parentheses

    np_acts-logits-general · gemini-2.0-flash

    section references

    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
     $_"
    -1.20
     myſelf
    -1.18
     Efq
    -1.16
    NUMX
    -1.11
    ^(@)
    -1.09
    ſelf
    -1.08
     ―――――
    -1.06
    neſs
    -1.04
     iſt
    -1.03
     raiſ
    -1.03
    POSITIVE LOGITS
    �
    0.93
    <eos>
    0.79
    ?
    0.72
     ;
    0.72
     ?
    0.69
    \
    0.68
    (
    0.67
    !
    0.66
    "
    0.65
    ~
    0.65
    Activations Density 0.299%

    No Known Activations