© 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. 3155
    Prev
    Next
    INDEX
    Explanations

    chemical ratios and proportions used in experimental methods

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

    Numerical ratios

    np_acts-logits-general · gemini-2.0-flash

    numerical ratios

    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
    ########.
    -0.64
    RegistryLite
    -0.63
    AndEndTag
    -0.58
    lielmo
    -0.58
    GOTREF
    -0.53
    Millisecond
    -0.52
    żer
    -0.51
    enko
    -0.50
    igraph
    -0.49
    testens
    -0.49
    POSITIVE LOGITS
     ratio
    2.96
     Ratio
    2.60
    ratio
    2.56
     ratios
    2.54
    Ratio
    2.40
     RATIO
    2.32
     Ratios
    2.25
    ratios
    2.11
    RATIO
    2.06
     proportion
    1.67
    Activations Density 0.646%

    No Known Activations