© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11471
    Prev
    Next
    INDEX
    Explanations

    processes related to organizational or procedural steps

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

    "process" or related terms

    np_acts-logits-general · gemini-2.0-flash

    process

    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
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.80
    ########.
    -0.53
     Rigidbody
    -0.50
     menyerang
    -0.49
    Distribuzione
    -0.48
     lái
    -0.48
    KeySpec
    -0.48
    ichord
    -0.48
     HasFactory
    -0.47
    valently
    -0.46
    POSITIVE LOGITS
     process
    4.01
    process
    3.53
     Process
    3.35
    Process
    3.21
     PROCESS
    3.07
     processes
    3.02
     proceso
    2.86
     processus
    2.81
     processo
    2.74
    PROCESS
    2.67
    Activations Density 0.543%

    No Known Activations