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. 129871
    Prev
    Next
    INDEX
    Explanations

    phrases related to choices and opportunities available to individuals

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

    opportunity or possibility

    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
    Demografie
    -0.43
    MessageTagHelper
    -0.38
     Deja
    -0.36
    jLabel
    -0.36
    tvguidetime
    -0.35
     jLabel
    -0.35
    DebuggerNonUser
    -0.35
    ibase
    -0.34
    сшта
    -0.33
    égard
    -0.33
    POSITIVE LOGITS
     mulighed
    1.45
     possibility
    1.45
     možnost
    1.42
     möjlighet
    1.41
     możliwość
    1.40
     possibilité
    1.39
     возможность
    1.38
     ability
    1.32
     opportunity
    1.32
     possibilità
    1.30
    Activations Density 0.102%

    No Known Activations