© 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. 22-GEMMASCOPE-RES-16K
    11. 8111
    Prev
    Next
    INDEX
    Explanations

    specific references to people and places, particularly related to Finnish culture and institutions

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

    before Finnish words

    np_acts-logits-general · gemini-2.0-flash

    Finnish words and academic contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Said
    -0.40
     super
    -0.39
    nare
    -0.38
     extra
    -0.38
     sind
    -0.37
    elang
    -0.37
     von
    -0.36
    mern
    -0.35
    dorfer
    -0.35
     said
    -0.35
    POSITIVE LOGITS
     betweenstory
    1.19
     Majefty
    1.06
     myſelf
    1.04
     purpoſe
    1.03
     CreateTagHelper
    1.02
    +#+#
    0.99
     uſed
    0.96
     itſelf
    0.95
     ſeveral
    0.94
     themſelves
    0.92
    Activations Density 0.065%

    No Known Activations