© 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. 21-GEMMASCOPE-RES-16K
    6. 8680
    Prev
    Next
    INDEX
    Explanations

    instances of the word "be" and its various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.84
     noDo
    -0.65
    basicConfig
    -0.64
     विश्वसनीयता
    -0.59
    PerformLayout
    -0.59
     teck
    -0.58
    SequentialGroup
    -0.57
    ὺς
    -0.56
    bootstrapcdn
    -0.56
    ,:);
    -0.55
    POSITIVE LOGITS
     sure
    0.89
     SURE
    0.66
     careful
    0.59
     warned
    0.59
     Sure
    0.58
     prepared
    0.54
    Sure
    0.53
    fitting
    0.52
     fair
    0.52
    sure
    0.51
    Activations Density 0.080%

    No Known Activations