© 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-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 11223
    Prev
    Next
    INDEX
    Explanations

    statements of belief or incredulity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.05
    CPtr
    -0.75
     تضيفلها
    -0.70
     ChromeDriver
    -0.70
    postsleuth
    -0.69
    Obrázky
    -0.67
     initComponents
    -0.65
     utafitiHapana
    -0.61
     Aristote
    -0.60
     Dionys
    -0.60
    POSITIVE LOGITS
     disbelief
    0.68
    想不到
    0.59
     unbelievable
    0.57
    believable
    0.57
    沒想到
    0.56
    incredible
    0.56
    guess
    0.56
    没想到
    0.55
     guess
    0.54
    Believe
    0.51
    Activations Density 0.244%

    No Known Activations