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. 9-GEMMASCOPE-RES-16K
    6. 1605
    Prev
    Next
    INDEX
    Explanations

    actions related to attempting or trying new things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.65
    tagHelper
    -0.61
    ailleurs
    -0.59
    SOUNDBITE
    -0.58
     also
    -0.56
     zelfs
    -0.54
     certainly
    -0.53
    ınd
    -0.53
     sogar
    -0.52
    stunde
    -0.52
    POSITIVE LOGITS
     Просто
    1.08
     Simplemente
    1.07
     simply
    1.03
    simply
    0.96
    Simply
    0.95
     simplemente
    0.94
    Einfach
    0.93
    Просто
    0.92
     simplesmente
    0.92
     Simply
    0.88
    Activations Density 0.366%

    No Known Activations