© 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. 2982
    Prev
    Next
    INDEX
    Explanations

    questions or statements reflecting uncertainty or requests for assistance

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

    Requests for assistance

    np_acts-logits-general · gemini-2.0-flash

    anybody, anyone, or help

    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
     yourself
    -0.58
     Ihnen
    -0.57
     comigo
    -0.57
     YOURSELF
    -0.55
    Portale
    -0.54
     riserv
    -0.53
     Yourself
    -0.53
    yourself
    -0.53
     giornal
    -0.51
    たしか
    -0.49
    POSITIVE LOGITS
     any
    1.13
     anyone
    1.10
     Any
    1.09
     Anybody
    1.06
     Anyone
    1.05
    Any
    1.03
     anybody
    1.02
    Anyone
    1.02
     HELP
    1.00
    Anybody
    0.99
    Activations Density 0.383%

    No Known Activations