© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5771
    Prev
    Next
    INDEX
    Explanations

    phrases indicating methods or means of achieving goals or objectives

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

    Mentions "means" or "way"

    np_acts-logits-general · gemini-2.0-flash

    methods and ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     operazioni
    -0.47
    LOYEES
    -0.46
    ONAUT
    -0.46
    InSection
    -0.43
    ollection
    -0.40
     darb
    -0.40
     opérations
    -0.38
     operações
    -0.38
     Verordnung
    -0.37
     operasi
    -0.36
    POSITIVE LOGITS
     Means
    0.69
    Means
    0.69
    手段
    0.67
    MigrationBuilder
    0.67
    bootstrapcdn
    0.67
     moyen
    0.66
     MEANS
    0.65
     means
    0.65
     ways
    0.64
    Ways
    0.62
    Activations Density 0.387%

    No Known Activations