© 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. 14-GEMMASCOPE-RES-16K
    6. 8567
    Prev
    Next
    INDEX
    Explanations

    terms related to image manipulation and scaling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.58
     ब्रेकडाउन
    -0.53
    ReusableCell
    -0.48
    enseits
    -0.48
     للاسماء
    -0.47
    ptonshire
    -0.44
    理石
    -0.44
    KommentareTeilen
    -0.44
    новништво
    -0.44
     intptr
    -0.44
    POSITIVE LOGITS
     zoom
    0.71
     scaling
    0.69
     SCALE
    0.69
    Scale
    0.68
     scale
    0.68
    scale
    0.67
     resize
    0.66
    Zoom
    0.65
    scaled
    0.64
    resize
    0.63
    Activations Density 0.405%

    No Known Activations