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

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K
    6. 1950
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical theories and algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.99
    >*/
    -0.90
    MessageTagHelper
    -0.84
    /**
    -0.82
     poffible
    -0.78
    Linki
    -0.78
     obfer
    -0.77
    醐
    -0.77
    ArrowToggle
    -0.77
    ">/
    -0.76
    POSITIVE LOGITS
     CH
    1.03
     ch
    0.94
    Ch
    0.91
     Chávez
    0.91
     Ch
    0.91
     CHAM
    0.90
     Cha
    0.89
     Chamb
    0.89
    Cha
    0.88
    CH
    0.85
    Activations Density 0.698%

    No Known Activations