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. 5883
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly in a political or historical context

    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
    GEBURTSDATUM
    -0.76
    Personendaten
    -0.75
     nahilalakip
    -0.75
    ✨:
    -0.72
     оригіналу
    -0.70
     ویکی‌پدیای
    -0.68
     MainAxisSize
    -0.66
     Walkover
    -0.65
    Tikang
    -0.64
     ModelExpression
    -0.64
    POSITIVE LOGITS
    1
    1.22
    0
    1.03
    2
    0.94
    th
    0.57
    openqa
    0.51
     Mule
    0.46
    minutos
    0.45
    tmpdir
    0.45
    something
    0.42
    3
    0.42
    Activations Density 0.229%

    No Known Activations