© 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. 28-GEMMASCOPE-RES-16K
    6. 7763
    Prev
    Next
    INDEX
    Explanations

    instances of the word "up" and its variations, indicating a focus on increases or upward trends

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

    "Up" followed by "to" or another word

    np_acts-logits-general · gemini-2.0-flash

    up to, up-shifted, up-regulated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.40
    FileDescriptor
    -0.40
     Савезне
    -0.39
    Demografie
    -0.39
    elemField
    -0.38
    Климат
    -0.37
    Domin
    -0.37
    Pads
    -0.37
     médicaux
    -0.36
     sei
    -0.36
    POSITIVE LOGITS
     Up
    0.81
    Up
    0.66
     UP
    0.59
     Down
    0.59
     giù
    0.58
     down
    0.58
     up
    0.55
    ⬆
    0.54
     DOWN
    0.53
    ISupport
    0.53
    Activations Density 0.157%

    No Known Activations