© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11239
    Prev
    Next
    INDEX
    Explanations

    terms related to connections and networking

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

    "Connect" and "connection"

    np_acts-logits-general · gemini-2.0-flash

    connection diagrams and signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Steering experiments: Gemma 2-2B / 10-GEMMASCOPE-RES-16K

    No Comments

    Negative Logits
    PerformLayout
    -0.80
     nahilalakip
    -0.74
    ToBounds
    -0.73
     ivelany
    -0.72
    GraphicsUnit
    -0.72
     GoogleFonts
    -0.70
    ambique
    -0.69
     UnityEditor
    -0.69
    CompilerServices
    -0.69
    paravant
    -0.68
    POSITIVE LOGITS
     Connections
    0.82
     connections
    0.79
     dots
    0.78
     CONNECT
    0.76
     Connecting
    0.76
     conn
    0.73
     reconnect
    0.73
     getConnection
    0.72
    Connecting
    0.72
    connections
    0.72
    Activations Density 0.101%

    No Known Activations