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. 19-GEMMASCOPE-RES-16K
    6. 15669
    Prev
    Next
    INDEX
    Explanations

    occurrences of the name "Ben" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gynhyrchwyd
    -0.61
    RegistryLite
    -0.57
    wira
    -0.53
    microb
    -0.51
    StructEnd
    -0.51
    Посилання
    -0.50
    SerializedName
    -0.49
    -------------</
    -0.49
    liebte
    -0.48
     saites
    -0.48
    POSITIVE LOGITS
     Ben
    1.08
     ben
    1.07
     BEN
    1.04
    BEN
    1.02
    Ben
    1.01
    ben
    0.97
     pinulongan
    0.79
    Bene
    0.77
     benches
    0.75
     Bens
    0.75
    Activations Density 0.062%

    No Known Activations