© 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. 18-GEMMASCOPE-RES-16K
    11. 2193
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific processes and relationships in biological systems

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

    semantically similar to "therefore"

    np_acts-logits-general · gemini-2.0-flash

    consequence or subsequent state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     והוא
    -1.19
     and
    -1.16
    性和
    -1.06
    이고
    -1.05
    并且
    -0.92
     และ
    -0.92
    ConstraintMaker
    -0.89
     &&
    -0.86
     And
    -0.84
    并将
    -0.84
    POSITIVE LOGITS
     accordingly
    0.90
     thereafter
    0.71
     withal
    0.62
     therefrom
    0.60
     therewith
    0.60
     afterwards
    0.55
    hyrchwyd
    0.53
     correspondingly
    0.53
    ">—
    0.53
     afterward
    0.53
    Activations Density 2.289%

    No Known Activations