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. 28-GEMMASCOPE-RES-16K
    6. 4112
    Prev
    Next
    INDEX
    Explanations

    quantitative changes and statistical measures in data

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

    Change, difference, or jump magnitude

    np_acts-logits-general · gemini-2.0-flash

    Δ symbol for differences

    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
     linkovi
    -0.41
     createSprite
    -0.40
     Савезне
    -0.38
    Cyfarwyddwr
    -0.37
     /\.(
    -0.36
     hasard
    -0.35
    RTLI
    -0.35
    }}]{
    -0.35
     pinulongan
    -0.35
     intérieur
    -0.35
    POSITIVE LOGITS
     difference
    1.30
     differences
    1.14
    difference
    1.12
    Difference
    1.08
     Difference
    1.05
    差
    1.04
     Differences
    0.99
     DIFFERENCE
    0.98
     differential
    0.97
    differences
    0.96
    Activations Density 1.592%

    No Known Activations