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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 8210
    Prev
    Next
    INDEX
    Explanations

    questions and statements related to self-reflection and social interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.55
    ///</
    -0.50
    iconque
    -0.50
    Did
    -0.48
    ついて
    -0.46
    illable
    -0.45
    WEBPACK
    -0.45
    blurRadius
    -0.45
    żna
    -0.45
     étions
    -0.45
    POSITIVE LOGITS
     don
    2.36
     doesn
    1.81
    don
    1.71
    Don
    1.42
     Don
    1.40
    doesn
    1.35
     DON
    1.30
    DON
    1.25
     won
    1.21
     Doesn
    1.16
    Activations Density 0.433%

    No Known Activations