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. 3-GEMMASCOPE-RES-16K
    6. 16284
    Prev
    Next
    INDEX
    Explanations

    strong emphasis on absolute or total descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vstack
    -0.50
     Gardiner
    -0.48
     very
    -0.47
     Guia
    -0.46
     pilas
    -0.46
    onload
    -0.45
    very
    -0.45
     zelo
    -0.44
    zeros
    -0.44
     totally
    -0.43
    POSITIVE LOGITS
    NameInMap
    0.88
    StoryboardSegue
    0.82
     contextLoads
    0.80
    aarrggbb
    0.77
    ConstraintMaker
    0.77
     kasarigan
    0.76
    #+#
    0.73
     Normdatei
    0.72
     joaat
    0.72
    '],
    
    0.71
    Activations Density 0.358%

    No Known Activations