© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 38647
    Prev
    Next
    INDEX
    Explanations

    concepts related to faith and repentance within a spiritual context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]}>
    -0.59
     الاف
    -0.59
     \]
    -0.59
     Cim
    -0.58
    Spice
    -0.57
     Aufg
    -0.56
    POLE
    -0.56
     hint
    -0.54
    pim
    -0.54
     []),
    -0.53
    POSITIVE LOGITS
    SequentialGroup
    0.81
     لينك
    0.67
    rrggbb
    0.66
    UrlResolution
    0.59
     accepté
    0.59
     refusé
    0.57
    libft
    0.56
     croire
    0.56
     parlé
    0.56
     bootloader
    0.56
    Activations Density 0.019%

    No Known Activations