© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2672
    Prev
    Next
    INDEX
    Explanations

    references to individuals in positions of authority or prominence in discussions

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

    Sentences about what "he" does or says

    np_acts-logits-general · gemini-2.0-flash

    he followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     say
    -1.17
     says
    -1.09
     said
    -1.07
    Says
    -1.06
    Said
    -1.02
     Says
    -1.00
    says
    -0.97
     SAID
    -0.96
    said
    -0.95
     saying
    -0.95
    POSITIVE LOGITS
    ImageContext
    0.79
    SourceChecksum
    0.74
     pihaknya
    0.69
     regretted
    0.69
    AndEndTag
    0.68
     werde
    0.66
    PostExecute
    0.64
     fossero
    0.64
    LEncoder
    0.64
     hoped
    0.63
    Activations Density 0.216%

    No Known Activations