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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 13827
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic variation and selection in populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $\
    -0.51
     неба
    -0.47
     non
    -0.45
    !
    -0.44
    ?
    -0.43
     typedef
    -0.41
    *(
    -0.40
     C
    -0.40
    tiera
    -0.39
     Росси
    -0.39
    POSITIVE LOGITS
    GEBURTSDATUM
    1.17
     صوتيه
    1.09
    tagHelperRunner
    1.01
     separately
    1.01
    DeleteBehavior
    1.00
     individually
    0.98
    Personendaten
    0.98
    Personensuche
    0.97
     مشين
    0.96
    LookAnd
    0.95
    Activations Density 0.970%

    No Known Activations