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. 13321
    Prev
    Next
    INDEX
    Explanations

    elements or concepts related to basketball training and shooting improvement devices

    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
    fillType
    -0.45
     iParam
    -0.42
     Савезне
    -0.41
    ngdoc
    -0.39
    клопе
    -0.38
     gabbana
    -0.36
     ब्रेकडाउन
    -0.36
     Screening
    -0.35
     trattano
    -0.34
     gad
    -0.34
    POSITIVE LOGITS
     practiced
    1.48
     practicing
    1.46
     practice
    1.44
    practi
    1.36
    practice
    1.36
     practised
    1.35
    Practice
    1.34
     practising
    1.31
     PRACTICE
    1.29
    Practi
    1.29
    Activations Density 0.396%

    No Known Activations