© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 4037
    Prev
    Next
    INDEX
    Explanations

    statements of belief or assertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     addSubview
    -0.46
     sèche
    -0.36
     صفحۀ
    -0.30
     את
    -0.30
     Réponses
    -0.29
    peicher
    -0.29
     Nhưng
    -0.29
    bekistan
    -0.28
    hisattva
    -0.28
     fantasía
    -0.28
    POSITIVE LOGITS
     reputed
    1.00
     rumored
    0.99
     believed
    0.97
     reportedly
    0.92
     known
    0.90
     rumoured
    0.87
     supposedly
    0.87
     allegedly
    0.84
     KNOWN
    0.84
     Known
    0.83
    Activations Density 0.341%

    No Known Activations