Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 8221
    Prev
    Next
    INDEX
    Explanations

    expressions of appreciation and compliments related to various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows intensifiers ("so", "such", "really")

    np_acts-logits-general · gemini-2.0-flash

    forms of "to be" followed by "such" or "so"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.74
    AnchorStyles
    -0.69
     CreateTagHelper
    -0.68
    LookAnd
    -0.63
    
    -0.61
    kmäler
    -0.61
     ***!
    -0.60
    
    -0.59
     Bourgoin
    -0.59
    TryParse
    -0.57
    POSITIVE LOGITS
     such
    1.51
     SUCH
    1.26
    such
    1.24
     so
    1.23
    Such
    1.23
     Such
    1.22
     SO
    0.97
     soo
    0.95
     sooo
    0.90
     tellement
    0.90
    Activations Density 0.145%

    No Known Activations