© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 7485
    Prev
    Next
    INDEX
    Explanations

    instances of the word "keeping" and its variations in relation to maintaining processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ፩
    -0.41
     gesteld
    -0.41
     समीक्षाओं
    -0.41
    DisplayMetrics
    -0.38
     tarjo
    -0.37
    iedene
    -0.37
     colonias
    -0.37
    ("")]
    -0.37
     pungkas
    -0.36
     pungkasnya
    -0.36
    POSITIVE LOGITS
     Keeping
    0.69
    Keeping
    0.68
     holding
    0.65
    Holding
    0.63
     kept
    0.62
     Keep
    0.61
     Las
    0.60
     Kept
    0.60
    kept
    0.60
     keeping
    0.59
    Activations Density 1.678%

    No Known Activations