© 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. 20-GEMMASCOPE-RES-16K
    6. 2429
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "become" and its variations

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

    verbs indicating transformation or change, particularly "become".

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     espé
    -0.51
    printStats
    -0.48
     pylint
    -0.48
    logError
    -0.48
     ſche
    -0.47
     StyleSheet
    -0.47
    onMouse
    -0.46
     Surveys
    -0.44
     Refunds
    -0.44
    SerializeField
    -0.44
    POSITIVE LOGITS
    become
    1.26
     become
    1.20
     Become
    1.15
    Become
    1.13
    becomes
    1.13
     becomes
    1.13
     becoming
    1.05
    became
    1.02
     became
    1.02
    becoming
    1.00
    Activations Density 0.058%

    No Known Activations