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. 23-GEMMASCOPE-RES-16K
    6. 11738
    Prev
    Next
    INDEX
    Explanations

    verbs denoting possession or state of being related to current or past actions

    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
     brought
    -0.79
    Answered
    -0.78
     created
    -0.77
     introduced
    -0.72
     made
    -0.69
     killed
    -0.67
     performed
    -0.67
     pushed
    -0.67
     moved
    -0.66
     picked
    -0.66
    POSITIVE LOGITS
     been
    1.63
    been
    1.22
     BEEN
    1.15
     Been
    1.07
     été
    1.07
    Been
    1.04
     be
    1.03
     stata
    0.92
     stato
    0.91
     быть
    0.88
    Activations Density 0.208%

    No Known Activations