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. 17-GEMMASCOPE-RES-16K
    6. 5175
    Prev
    Next
    INDEX
    Explanations

    collective actions and experiences involving groups of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aveug
    -0.62
    ercizio
    -0.59
     themſelves
    -0.59
     validamos
    -0.55
     wrists
    -0.53
     felling
    -0.53
     Psyche
    -0.53
     perſon
    -0.52
    dersfield
    -0.52
     Cæsar
    -0.52
    POSITIVE LOGITS
     together
    0.69
     both
    0.69
     discussed
    0.67
     discussion
    0.67
     I
    0.61
     he
    0.61
     juntos
    0.60
     Both
    0.59
     discuss
    0.58
     jointly
    0.58
    Activations Density 0.367%

    No Known Activations