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. 11286
    Prev
    Next
    INDEX
    Explanations

    modal verbs and their associated forms in relation to obligations or conditions

    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
    Originally
    -0.47
     transfieras
    -0.47
    Rhestr
    -0.45
    емость
    -0.44
    Референце
    -0.43
     StringTokenizer
    -0.43
     Treated
    -0.43
    manteau
    -0.43
    mbing
    -0.42
     tromper
    -0.42
    POSITIVE LOGITS
     present
    0.88
     needed
    0.88
     forthcoming
    0.84
     possible
    0.84
     provided
    0.80
     evident
    0.80
     apparent
    0.77
     available
    0.77
     being
    0.76
     created
    0.73
    Activations Density 0.703%

    No Known Activations