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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 9812
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical instructions or code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.49
     bailando
    -0.46
    TINGS
    -0.44
    참고
    -0.44
     обрабаты
    -0.43
     precisione
    -0.43
     limpi
    -0.43
    踊
    -0.43
    lüğ
    -0.43
    Semitism
    -0.43
    POSITIVE LOGITS
    การ
    0.82
     การ
    0.62
     disambiguazione
    0.60
     Chwiliwch
    0.54
     việc
    0.50
     sự
    0.48
    +#+#
    0.43
     bukanlah
    0.40
     elaboration
    0.39
     Alquiler
    0.38
    Activations Density 0.069%

    No Known Activations