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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15692
    Prev
    Next
    INDEX
    Explanations

    references to divine experiences and communication with God

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     defaultstate
    -0.42
    complexContent
    -0.41
    RegressionTest
    -0.39
    ToScroll
    -0.36
    ButtonItem
    -0.36
    lwjgl
    -0.35
    ❦
    -0.35
    ngOnDestroy
    -0.34
    Subviews
    -0.34
     Feu
    -0.33
    POSITIVE LOGITS
     resourceCulture
    0.56
    Ligações
    0.52
    BASEPATH
    0.52
     prays
    0.49
    ortecedor
    0.47
     agujas
    0.47
    worship
    0.47
    delwed
    0.45
     beginnetje
    0.45
    RegistryLite
    0.45
    Activations Density 0.304%

    No Known Activations