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. 10-GEMMASCOPE-RES-16K
    6. 4559
    Prev
    Next
    INDEX
    Explanations

    affirmative or interrogative phrases and auxiliary verbs indicating capability or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EdgeInsets
    -0.63
     "
    -0.61
     <<<<<<<<<<<<<<
    -0.60
    offsetWidth
    -0.58
    AppRoutingModule
    -0.56
     the
    -0.56
    BuildContext
    -0.53
    evich
    -0.52
     Taktlose
    -0.52
    zustellen
    -0.50
    POSITIVE LOGITS
    \{\\
    0.97
    providedIn
    0.87
     виправивши
    0.74
    BIÉN
    0.74
     you
    0.72
     entomo
    0.69
    CloseOperation
    0.69
     autorytatywna
    0.66
     ornith
    0.66
    存于互联网档案馆
    0.65
    Activations Density 0.267%

    No Known Activations