© 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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 3974
    Prev
    Next
    INDEX
    Explanations

    phrases indicating hypothetical or projected situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     UnityEditor
    -0.63
     mắn
    -0.58
     ujednoznacz
    -0.58
    zyg
    -0.56
    DMETHOD
    -0.56
    componentDid
    -0.53
     đời
    -0.52
    Gön
    -0.52
    elesai
    -0.52
    wpdb
    -0.50
    POSITIVE LOGITS
     imagining
    1.39
     scenarios
    1.37
     envision
    1.36
     imagined
    1.34
     envisage
    1.32
     Scenarios
    1.31
     envisioned
    1.30
     imaginations
    1.27
     imagines
    1.24
     imagination
    1.20
    Activations Density 0.096%

    No Known Activations