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. 12-GEMMASCOPE-RES-16K
    6. 6473
    Prev
    Next
    INDEX
    Explanations

    technical terminology and concepts related to engineering and technology, particularly in the context of production and machinery

    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
    GraphicsUnit
    -0.87
    GenerationType
    -0.80
    Geplaatst
    -0.74
     raiſ
    -0.73
    تقاوى
    -0.73
    IonicModule
    -0.71
     Efq
    -0.71
    chastic
    -0.69
    ustimmung
    -0.69
    SuppressLint
    -0.69
    POSITIVE LOGITS
     confidentialité
    0.43
    様
    0.43
     vanguardia
    0.41
    點
    0.40
    …
    0.39
     právě
    0.38
     satunya
    0.38
    //
    0.38
    </h2>
    0.37
     pomocą
    0.36
    Activations Density 0.979%

    No Known Activations