© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 7751
    Prev
    Next
    INDEX
    Explanations

    mathematical summation expressions and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    titleMargin
    -0.39
    benhavn
    -0.39
    olphe
    -0.38
    ||}
    -0.36
     santo
    -0.34
     madam
    -0.34
     propa
    -0.34
    iermark
    -0.34
    的地方
    -0.33
     financières
    -0.33
    POSITIVE LOGITS
    帖最后由
    0.59
    UrlResolution
    0.58
    存于互联网档案馆
    0.56
     utafitiHapana
    0.54
    KURZBESCHREIBUNG
    0.53
    Diweddarwch
    0.48
     فريبيس
    0.46
     հղումներ
    0.45
    లాలు
    0.44
     noDo
    0.44
    Activations Density 0.909%

    No Known Activations