© 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. 25-GEMMASCOPE-RES-16K
    11. 3667
    Prev
    Next
    INDEX
    Explanations

    named entities, particularly related to geographical locations and economic indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hooker
    -0.58
     unknownFields
    -0.56
     Donegal
    -0.53
    二郎
    -0.52
     Bulgarian
    -0.52
     Iliad
    -0.51
    jeeling
    -0.51
    stdafx
    -0.51
    bog
    -0.49
     Dao
    -0.49
    POSITIVE LOGITS
     Saudi
    1.37
     Sau
    1.21
    Saudi
    1.20
     Kingdom
    1.20
     kingdom
    1.14
     King
    1.12
     Riyadh
    1.11
    Kingdom
    1.02
    Sau
    1.01
     Prince
    1.01
    Activations Density 0.250%

    No Known Activations