© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8886
    Prev
    Next
    INDEX
    Explanations

    numeric values and statistical data within the text

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

    Numbers followed by mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    numbers with units like mol or sec

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.63
     propOrder
    -0.60
     Infórmanos
    -0.58
     protoimpl
    -0.53
    PyExc
    -0.52
     nahilalakip
    -0.52
     Walkover
    -0.52
    LookAnd
    -0.51
    __((
    -0.50
     Exacts
    -0.49
    POSITIVE LOGITS
     ProtoMessage
    0.38
     dår
    0.37
     gerais
    0.36
    Demografia
    0.35
     čase
    0.35
     peores
    0.32
    Poor
    0.32
     résolution
    0.31
     touristes
    0.31
    poor
    0.31
    Activations Density 0.661%

    No Known Activations