© 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. 4-GEMMASCOPE-RES-16K
    11. 984
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs that describe depth and breadth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.60
    ьаж
    -0.54
     espor
    -0.51
    évaluateur
    -0.51
    انيف
    -0.51
     ModelExpression
    -0.48
     Yugoslavia
    -0.48
     переписи
    -0.47
     Curitiba
    -0.46
    DataPropertyName
    -0.46
    POSITIVE LOGITS
     deepest
    1.16
     deepen
    1.15
     deeper
    1.11
     deep
    1.10
     depth
    1.07
     deepened
    1.06
     deepening
    1.05
     Deeper
    1.02
     Depth
    0.99
    deep
    0.99
    Activations Density 0.404%

    No Known Activations