© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11491
    Prev
    Next
    INDEX
    Explanations

    statements about objectives, aims, or goals

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

    "goal", "aim", "objective"

    np_acts-logits-general · gemini-2.0-flash

    expressing an aim or goal

    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
     ModelExpression
    -0.78
     BrowserModule
    -0.78
    msgTypes
    -0.70
    Diweddarwch
    -0.70
     fileList
    -0.69
     témoig
    -0.68
    ſſung
    -0.67
    __(/*!
    -0.66
     pajero
    -0.66
     שוליים
    -0.66
    POSITIVE LOGITS
     aim
    1.21
     aims
    1.05
     goal
    1.02
     intention
    0.96
     aiming
    0.96
    Aim
    0.92
     purpose
    0.91
     Tujuan
    0.91
     objetivo
    0.90
    objectif
    0.89
    Activations Density 0.395%

    No Known Activations