© 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. 23-GEMMASCOPE-RES-16K
    6. 5553
    Prev
    Next
    INDEX
    Explanations

    phrases related to connections and relationships between ideas or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    other
    -0.52
     Pristupljeno
    -0.52
    others
    -0.51
     other
    -0.50
    Other
    -0.50
    parsedMessage
    -0.48
     otros
    -0.45
     otras
    -0.45
    Others
    -0.43
    FieldDescriptor
    -0.43
    POSITIVE LOGITS
     motivation
    0.91
     expertise
    0.91
     purpose
    0.91
     direction
    0.90
     inspiration
    0.88
     kasarigan
    0.85
     capabilities
    0.83
     responsibility
    0.83
     ambition
    0.82
     expectations
    0.81
    Activations Density 0.372%

    No Known Activations