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. 2311
    Prev
    Next
    INDEX
    Explanations

    components related to programming and software structure

    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
     ligiloj
    -0.68
     bı
    -0.65
     Picchu
    -0.59
     bırak
    -0.58
    scissors
    -0.57
     assoluto
    -0.55
     bArr
    -0.55
     Blum
    -0.55
    ._.
    -0.54
    tenths
    -0.53
    POSITIVE LOGITS
    PrototypeOf
    0.74
    Tikang
    0.69
    tagHelper
    0.69
    getDoctrine
    0.69
    zsche
    0.68
     BoxDecoration
    0.63
     lenker
    0.61
    +:+
    0.61
    Twig
    0.61
    \
    0.58
    Activations Density 0.039%

    No Known Activations