© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12388
    Prev
    Next
    INDEX
    Explanations

    phrases related to progress or journey, particularly focusing on the concept of 'finding one's way'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.71
     Preferencias
    -0.69
    TypedDataSet
    -0.61
     насељу
    -0.57
    addCriterion
    -0.54
    TagMode
    -0.53
    IsMutable
    -0.53
    <bos>
    -0.52
    intios
    -0.51
     كومونز
    -0.49
    POSITIVE LOGITS
     way
    1.54
    way
    1.16
    Way
    1.02
     WAY
    0.95
     Way
    0.92
     caminho
    0.89
    WAY
    0.88
     camino
    0.85
     väg
    0.75
     путь
    0.67
    Activations Density 0.168%

    No Known Activations