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. 6-GEMMASCOPE-RES-16K
    6. 2501
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of reality versus expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <%@
    -0.46
    الدراسه
    -0.44
    ushes
    -0.43
    fsch
    -0.43
    Cyfeiriadau
    -0.43
     ویکی
    -0.42
    zież
    -0.42
    romas
    -0.41
    MENAFN
    -0.41
    yntaxException
    -0.41
    POSITIVE LOGITS
    实际
    1.15
    actual
    1.12
     actuality
    1.11
     réalité
    1.10
    Actual
    1.10
     reality
    1.08
    實際
    1.07
     Actual
    1.05
     actual
    1.03
     ACTUAL
    1.01
    Activations Density 0.408%

    No Known Activations