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. 19-GEMMASCOPE-RES-16K
    6. 11235
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ability, options, or potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Obvious
    -0.87
     ovviamente
    -0.76
     obvious
    -0.74
     natuurlijk
    -0.71
     seems
    -0.70
     says
    -0.70
     понятно
    -0.69
     wydaje
    -0.69
     seemed
    -0.69
     ensures
    -0.68
    POSITIVE LOGITS
     indeed
    1.25
     efectivamente
    1.14
    indeed
    1.02
     inderdaad
    0.96
     للمعارف
    0.81
     وأن
    0.79
     tatsächlich
    0.77
     faktisk
    0.75
     actually
    0.74
     تانيه
    0.72
    Activations Density 1.230%

    No Known Activations