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. 12303
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "wait."

    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
     BoxFit
    -0.86
     للاسماء
    -0.76
    writeFieldEnd
    -0.75
    IndentedString
    -0.73
     ModelExpression
    -0.73
    Personendaten
    -0.73
    __(/*!
    -0.72
    DeleteBehavior
    -0.70
    principalColumn
    -0.68
    #+#
    -0.68
    POSITIVE LOGITS
     patiently
    0.97
     impatiently
    0.77
    listed
    0.65
    list
    0.65
     longer
    0.63
     until
    0.62
     anxiously
    0.62
     Pati
    0.60
     PATIENT
    0.59
     paciente
    0.58
    Activations Density 0.075%

    No Known Activations