© 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-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9388
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or skepticism about the capabilities of corporations and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    featureID
    -0.45
     кое
    -0.39
     slightly
    -0.36
     actionMode
    -0.35
    newArrayList
    -0.34
     nieco
    -0.34
    ंदीखरीदारी
    -0.33
    UnknownFieldSet
    -0.32
     minim
    -0.32
     emphas
    -0.32
    POSITIVE LOGITS
    suddenly
    0.70
    GEBURTSDATUM
    0.69
     suddenly
    0.68
     magically
    0.65
     risking
    0.60
    Suddenly
    0.57
    わざわざ
    0.57
     soudain
    0.56
     Suddenly
    0.55
     risked
    0.55
    Activations Density 0.450%

    No Known Activations