Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 13929
    Prev
    Next
    INDEX
    Explanations

    words related to confirmation or verification of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enzie
    -0.70
    Rok
    -0.66
     Sk
    -0.65
    duction
    -0.65
     She
    -0.64
    z
    -0.63
     tas
    -0.62
    She
    -0.62
     Rok
    -0.61
    Tas
    -0.61
    POSITIVE LOGITS
     Confirm
    1.40
     confirmations
    1.37
     confirms
    1.28
     Confirmation
    1.27
     confirm
    1.26
     verifies
    1.26
     Confirmed
    1.24
     confirmation
    1.23
    CONFIRM
    1.22
     confirmed
    1.19
    Activations Density 0.146%

    No Known Activations