© 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. 5683
    Prev
    Next
    INDEX
    Explanations

    conversational phrases and interactions, particularly those involving questioning and response dynamics

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

    Agreement or acceptance indicators

    np_acts-logits-general · gemini-2.0-flash

    acknowledging questions

    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
     '\\;'
    -0.63
    Хьажоргаш
    -0.62
    Personendaten
    -0.60
     ModelRenderer
    -0.60
     createSprite
    -0.58
    @[+][
    -0.57
    DOCTYPE
    -0.53
     Gron
    -0.52
     ligiloj
    -0.52
     springfox
    -0.51
    POSITIVE LOGITS
     okay
    2.18
     ok
    2.18
     OK
    2.16
     Okay
    1.94
     alright
    1.88
    Okay
    1.85
    Ok
    1.84
     Ok
    1.84
    OK
    1.82
    okay
    1.75
    Activations Density 0.236%

    No Known Activations