© 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. 31-GEMMASCOPE-RES-16K
    6. 3635
    Prev
    Next
    INDEX
    Explanations

    instances of the word "do"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the auxiliary verb "do" used in first-person statements of opinion or experience.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ParallelGroup
    -0.32
    esModule
    -0.31
    __":
    
    -0.27
     lungo
    -0.27
     ...
    -0.26
    getLogger
    -0.26
    তথ্যসূত্র
    -0.26
     alatt
    -0.26
     дори
    -0.26
    __":
    -0.25
    POSITIVE LOGITS
     indígen
    0.83
     increí
    0.76
    síða
    0.74
     ſind
    0.72
     Geiſt
    0.69
    <unused14>
    0.69
    <unused52>
    0.68
    <unused28>
    0.68
     vooz
    0.68
    [@BOS@]
    0.68
    Activations Density 0.109%

    No Known Activations