© 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. 10-GEMMASCOPE-RES-16K
    6. 13601
    Prev
    Next
    INDEX
    Explanations

    phrases conveying reassurance and the absence of harm or danger

    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
    _));
    -0.56
    principalTable
    -0.54
     المعيارى
    -0.49
    LayoutStyle
    -0.49
    Datuak
    -0.48
    '][]
    -0.48
    ()]);
    -0.47
     تحقق
    -0.47
    )]);
    -0.47
    */].
    -0.45
    POSITIVE LOGITS
    Erreferentziak
    0.70
     Italijani
    0.60
    MultipartFile
    0.60
    ьаж
    0.59
     preocupes
    0.59
     needn
    0.59
    AxisAlignment
    0.58
     Normdatei
    0.57
     BorderRadius
    0.56
    IconModule
    0.55
    Activations Density 0.168%

    No Known Activations