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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 11776
    Prev
    Next
    INDEX
    Explanations

    phrases related to forgiveness and salvation within a religious context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.88
    abestanden
    -0.69
     متعلقه
    -0.68
    ReusableCell
    -0.64
     للمعارف
    -0.61
    tvguidetime
    -0.58
     يتيمه
    -0.57
    XmlAccessType
    -0.55
    WebControls
    -0.55
    Scénario
    -0.54
    POSITIVE LOGITS
     Jesus
    0.93
     God
    0.91
     verse
    0.89
     notice
    0.78
     Psalm
    0.77
     Verse
    0.76
    God
    0.74
    Verse
    0.74
     Notice
    0.72
    Jesus
    0.72
    Activations Density 0.120%

    No Known Activations