© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 1354
    Prev
    Next
    INDEX
    Explanations

    references to blessings and curses, particularly in a religious or spiritual context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ритори
    -0.44
     Manusia
    -0.32
     Bidang
    -0.32
     bege
    -0.32
    -0.32
     prisonniers
    -0.31
    providedIn
    -0.31
    Reference
    -0.31
    følgelig
    -0.30
     Interface
    -0.30
    POSITIVE LOGITS
     blessing
    1.30
     blessings
    1.27
    bless
    1.23
     Blessings
    1.22
     bless
    1.19
     BLESS
    1.19
     Blessing
    1.18
    Bless
    1.18
     Bless
    1.15
    Blessings
    1.08
    Activations Density 0.169%

    No Known Activations