© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14429
    Prev
    Next
    INDEX
    Explanations

    active verbs that indicate actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    third-person singular present-tense verbs ending in -s or -es.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    third-person singular present tense verbs (verbs ending in 's').

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    存于互联网档案馆
    -0.52
    Plural
    -0.42
     or
    -0.42
     opinion
    -0.41
    Credential
    -0.40
    Preference
    -0.40
     fubject
    -0.39
     ſub
    -0.38
     ſtate
    -0.38
     houſe
    -0.38
    POSITIVE LOGITS
     للمعارف
    0.85
     propOrder
    0.79
    roaches
    0.77
    cels
    0.75
    s
    0.74
    lishes
    0.73
    ixes
    0.73
    tifies
    0.72
    odes
    0.71
    lizes
    0.71
    Activations Density 0.599%

    No Known Activations