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. 11119
    Prev
    Next
    INDEX
    Explanations

    references to specific names, titles, and structural elements within a text

    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
     oxidase
    -0.52
     Económica
    -0.51
     bancaria
    -0.48
    Personendaten
    -0.48
     cristiana
    -0.47
     extranjera
    -0.47
     gratuite
    -0.46
     Justo
    -0.46
     azo
    -0.43
     Mónica
    -0.43
    POSITIVE LOGITS
    SequentialGroup
    0.69
    haustible
    0.68
    idered
    0.65
    EDEFAULT
    0.62
    ValueStyle
    0.59
    ugeot
    0.59
    NewUrlParser
    0.57
    SourceChecksum
    0.57
    IntoConstraints
    0.57
    )++;
    0.57
    Activations Density 0.040%

    No Known Activations