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. 25-GEMMASCOPE-RES-16K
    6. 3378
    Prev
    Next
    INDEX
    Explanations

    symbols and specific numerical values associated with measurements or data points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     برانيه
    -0.47
    richTextPanel
    -0.44
    OGND
    -0.41
    lccn
    -0.38
    VIAF
    -0.36
     Lehmann
    -0.36
    permitAll
    -0.35
    hotra
    -0.34
     Cavendish
    -0.34
     Horowitz
    -0.33
    POSITIVE LOGITS
     ss
    0.91
    Ss
    0.89
     sg
    0.89
     sr
    0.88
     getS
    0.87
    sS
    0.86
     sb
    0.86
    getS
    0.86
     SIS
    0.84
     Ss
    0.84
    Activations Density 12.899%

    No Known Activations