© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 727
    Prev
    Next
    INDEX
    Explanations

    references to legal rights and processes in relation to community awareness and individual actions

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

    phrases that indicate taking advantage of opportunities or offers

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

    take advantage, exploit, utilize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ########.
    -0.78
    IUrlHelper
    -0.64
    QMetaType
    -0.61
    JspWriter
    -0.59
    RegistryLite
    -0.58
    şam
    -0.53
    IsMutable
    -0.53
     صوتيه
    -0.52
    Controllo
    -0.51
    ReusableCell
    -0.50
    POSITIVE LOGITS
     utilization
    1.53
     availed
    1.47
     utilize
    1.43
     utilisation
    1.40
     Utilization
    1.39
     utilized
    1.34
     utilise
    1.27
     utilised
    1.25
     avail
    1.23
    utilized
    1.19
    Activations Density 0.214%

    No Known Activations