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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129880
    Prev
    Next
    INDEX
    Explanations

    phrases that suggest urgency or immediacy

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

    less is more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Географиясе
    -0.56
     CURIAM
    -0.49
    Jîn
    -0.42
    verwijspagina
    -0.41
    UnusedPrivate
    -0.38
    DebuggerStep
    -0.36
    دانشنامهٔ
    -0.36
     '/':
    -0.35
    TagMode
    -0.34
    Havolalar
    -0.33
    POSITIVE LOGITS
     is
    2.23
     isn
    1.05
     was
    0.91
     isnt
    0.81
     Is
    0.79
     adalah
    0.79
     является
    0.79
     ialah
    0.77
     wasn
    0.73
     là
    0.71
    Activations Density 0.067%

    No Known Activations