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. 38-GEMMASCOPE-RES-16K
    6. 7531
    Prev
    Next
    INDEX
    Explanations

    elements and functionalities related to data extraction and document management

    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
    ArrowToggle
    -0.56
    :✨
    -0.54
    protoimpl
    -0.52
     يتيمه
    -0.51
     समीक्षाओं
    -0.44
    )_/¯
    -0.43
    ConstraintMaker
    -0.43
     Autorisations
    -0.42
     rhestr
    -0.41
    StoryboardSegue
    -0.40
    POSITIVE LOGITS
     text
    3.56
     Text
    3.11
     texts
    2.86
    Text
    2.83
    text
    2.83
     TEXT
    2.80
     texte
    2.58
     texto
    2.55
     tekst
    2.53
    TEXT
    2.52
    Activations Density 0.812%

    No Known Activations