Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3326
    Prev
    Next
    INDEX
    Explanations

    the verb "become" and its various forms, signifying change or transformation

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

    "become" or its variations

    np_acts-logits-general · gemini-2.0-flash

    change of state

    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
    majánló
    -0.80
     Geiſt
    -0.73
    fieurs
    -0.68
     $_(
    -0.68
     dieſer
    -0.68
    síða
    -0.67
     ſche
    -0.67
     ſeine
    -0.66
     Waſſer
    -0.66
    ſchaft
    -0.65
    POSITIVE LOGITS
     become
    1.76
    become
    1.66
     becomes
    1.62
     Become
    1.59
    Become
    1.58
     becoming
    1.52
     became
    1.49
    becomes
    1.46
    Becoming
    1.43
     Becoming
    1.36
    Activations Density 0.121%

    No Known Activations