© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 81685
    Prev
    Next
    INDEX
    Explanations

    terms related to manipulation or the act of influencing something

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

    manipulate the world

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    ########.
    -0.45
     resultCode
    -0.44
    Soon
    -0.44
    avax
    -0.43
    =-=-=-=-
    -0.41
    Cron
    -0.40
    Year
    -0.40
    Frost
    -0.40
     imageNamed
    -0.40
     getDefault
    -0.39
    POSITIVE LOGITS
    manip
    1.30
     Manip
    1.26
     manipulation
    1.18
     manip
    1.17
     manipulate
    1.16
     manipulated
    1.15
     manipulating
    1.13
     manipulator
    1.11
    Manip
    1.11
    Manipulation
    1.10
    Activations Density 0.011%

    No Known Activations