© 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. 38-GEMMASCOPE-RES-16K
    6. 7875
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering or mechanical design

    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
     Numerade
    -0.43
    Manbalar
    -0.42
    SharedCtor
    -0.41
    historic
    -0.40
    zzleHttp
    -0.40
    లాలు
    -0.39
     belajar
    -0.39
    MenuInflater
    -0.38
    lectricité
    -0.38
    ⚐
    -0.37
    POSITIVE LOGITS
     width
    0.77
     geometry
    0.71
     widths
    0.68
     thickness
    0.66
     geometrical
    0.65
     dimensions
    0.65
     geometries
    0.64
     geomé
    0.62
     gaps
    0.60
     Width
    0.59
    Activations Density 1.892%

    No Known Activations