Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8391
    Prev
    Next
    INDEX
    Explanations

    references to the effects of radiation and other influences on biological mechanisms and gene expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.98
    rungsseite
    -0.93
    setVerticalGroup
    -0.82
    principalTable
    -0.82
     AssemblyCulture
    -0.81
    ChildScrollView
    -0.79
     GenerationType
    -0.76
    цездатний
    -0.75
    oa̍t
    -0.75
    Vidite
    -0.70
    POSITIVE LOGITS
     stimuli
    0.52
     stimulus
    0.49
     estí
    0.44
     induced
    0.41
     stimulation
    0.38
     trigger
    0.38
     induce
    0.37
     influence
    0.37
     воздействия
    0.35
     pressure
    0.34
    Activations Density 1.717%

    No Known Activations