© 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. 9-GEMMASCOPE-RES-16K
    6. 8890
    Prev
    Next
    INDEX
    Explanations

    technical terms related to audio and video encoding formats and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical terms related to image and video file formats, encoding, and compression technologies.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.52
    +#+#
    -0.51
     tartalomajánló
    -0.49
    adaptiveStyles
    -0.43
     Савезне
    -0.40
     ویکی‌پدی
    -0.39
     frock
    -0.38
    UserScript
    -0.38
    mphony
    -0.38
    ViewImports
    -0.37
    POSITIVE LOGITS
    compressed
    0.52
    HasAnnotation
    0.46
    AccessorTable
    0.46
     referrerpolicy
    0.44
    MathML
    0.43
    Compressed
    0.43
    StandardCharsets
    0.42
     BitmapFactory
    0.41
     dataType
    0.41
     Compressed
    0.41
    Activations Density 0.316%

    No Known Activations