© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7294
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning and execution

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

    "put" and its variations

    np_acts-logits-general · gemini-2.0-flash

    idiomatic use of 'put'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tää
    -0.43
    ยาก
    -0.39
     hoor
    -0.37
     enfans
    -0.36
    สร
    -0.35
     obro
    -0.34
     liberdade
    -0.34
     libertad
    -0.34
     Umgang
    -0.34
     evolução
    -0.34
    POSITIVE LOGITS
     put
    1.16
     Putting
    1.12
    Putting
    1.09
     putting
    1.08
     Put
    1.06
    putting
    1.05
     Puts
    1.02
    Put
    1.01
     puts
    1.01
     PUT
    0.95
    Activations Density 0.185%

    No Known Activations