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. 7-GEMMASCOPE-RES-16K
    6. 8861
    Prev
    Next
    INDEX
    Explanations

    mentions of folders or directory structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alnız
    -0.93
    BeginContext
    -0.92
     igång
    -0.90
    httphttps
    -0.88
    GEBURTSDATUM
    -0.87
    SupportActionBar
    -0.82
     Vos
    -0.82
    ืด
    -0.81
     useDispatch
    -0.80
    inerja
    -0.79
    POSITIVE LOGITS
     Folder
    0.80
     folder
    0.80
    aR
    0.75
    𝐦
    0.74
    𝐛
    0.71
     Reiche
    0.71
    وع
    0.70
    𝐚
    0.70
     resid
    0.68
    styleType
    0.67
    Activations Density 0.129%

    No Known Activations