© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 1678
    Prev
    Next
    INDEX
    Explanations

    interactions and comparisons related to political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.77
     autorytatywna
    -0.77
     архивлан
    -0.75
    TagMode
    -0.74
     DBNull
    -0.74
    Brainz
    -0.72
    ########.
    -0.67
     AssemblyProduct
    -0.65
    ValueStyle
    -0.64
     Administrativna
    -0.63
    POSITIVE LOGITS
     worst
    0.53
     worse
    0.53
    SequentialGroup
    0.45
     déjà
    0.44
     pas
    0.43
    o
    0.42
     fortunately
    0.41
     solder
    0.41
    lek
    0.41
     –
    0.41
    Activations Density 0.427%

    No Known Activations