© 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. 15702
    Prev
    Next
    INDEX
    Explanations

    the presence of the start of text or paragraphs

    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
    pele
    -0.51
     Audiodateien
    -0.51
    ormais
    -0.50
     Help
    -0.50
     Protector
    -0.50
    퀀
    -0.49
    NewGuid
    -0.49
     natin
    -0.48
     HELP
    -0.47
    Ever
    -0.47
    POSITIVE LOGITS
    <bos>
    0.73
    MessageTagHelper
    0.71
    JspWriter
    0.66
    MIDDLEWARE
    0.63
    CppMethod
    0.62
    IContainer
    0.55
     PeEnEo
    0.52
     bloat
    0.51
    IUrlHelper
    0.51
     Administrativna
    0.51
    Activations Density 0.029%

    No Known Activations