© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 867
    Prev
    Next
    INDEX
    Explanations

    conditional statements or phrases that indicate hypothetical situations

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

    "if" or "when" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    conditional statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    colgroup
    -0.34
    .*")]
    -0.33
    Referencias
    -0.31
     parti
    -0.29
     organiz
    -0.29
    ,
    -0.29
     aisle
    -0.29
     المل
    -0.29
     Mainland
    -0.28
     divisive
    -0.28
    POSITIVE LOGITS
    Personendaten
    0.78
     Мексичка
    0.69
     Infórmanos
    0.68
    AndEndTag
    0.66
    rungsseite
    0.63
     հղումներ
    0.61
     '\\;'
    0.59
    bitField
    0.59
    HasAnnotation
    0.58
    下载附件
    0.57
    Activations Density 0.398%

    No Known Activations