Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 16239
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and code attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otomatig
    -0.97
     surla
    -0.82
    EDEFAULT
    -0.82
    adaptiveStyles
    -0.75
     CanadaChoose
    -0.75
     дописавши
    -0.73
     Chwiliwch
    -0.73
    ⸮
    -0.73
    genodigd
    -0.73
    Personensuche
    -0.72
    POSITIVE LOGITS
     preserv
    0.36
     conserv
    0.36
     glor
    0.35
     Hawai
    0.34
     navig
    0.33
     chocol
    0.33
     Olymp
    0.33
     sacrific
    0.32
     celebr
    0.32
     histor
    0.32
    Activations Density 0.737%

    No Known Activations