© 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. 24-GEMMASCOPE-RES-16K
    11. 1588
    Prev
    Next
    INDEX
    Explanations

    terms related to health care and community support systems

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

    "Ch" followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    ch or channel

    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
     snippetHide
    -0.49
    UserScript
    -0.46
    strix
    -0.44
    뀌
    -0.43
    SHI
    -0.43
     ويكيميديا
    -0.43
    timmt
    -0.42
    cesz
    -0.42
    ijão
    -0.42
     sha
    -0.42
    POSITIVE LOGITS
     Ch
    3.38
    Ch
    3.20
     ch
    3.19
     CH
    2.55
    ch
    2.53
    CH
    2.26
     chan
    1.71
    chn
    1.57
     Channel
    1.54
    チャ
    1.53
    Activations Density 0.320%

    No Known Activations