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. 17-GEMMASCOPE-RES-16K
    6. 1137
    Prev
    Next
    INDEX
    Explanations

    activities and actions related to teaching and learning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.61
    }$_
    -0.49
     oferta
    -0.46
    StoryboardSegue
    -0.43
    urlopen
    -0.42
    check
    -0.41
    renda
    -0.41
    eckel
    -0.40
     NavController
    -0.40
    elly
    -0.39
    POSITIVE LOGITS
     basics
    1.13
     how
    1.09
     techniques
    0.89
    basics
    0.88
     basic
    0.87
    如何
    0.86
     básico
    0.85
    Basics
    0.84
     Basics
    0.84
     كيفية
    0.82
    Activations Density 0.265%

    No Known Activations