© 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. 7559
    Prev
    Next
    INDEX
    Explanations

    terms associated with destruction and loss

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

    Removal or disappearance

    np_acts-logits-general · gemini-2.0-flash

    completely gone

    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
     مشين
    -1.08
    ArgsConstructor
    -0.87
     חיצוניים
    -0.80
    SBATCH
    -0.80
     Réponses
    -0.78
     שוליים
    -0.76
     estekak
    -0.76
    Datuak
    -0.72
    сылкі
    -0.72
    numerusform
    -0.71
    POSITIVE LOGITS
     completely
    2.08
     altogether
    2.07
     entirely
    2.02
     Completely
    1.68
    completely
    1.68
    Completely
    1.56
     totally
    1.52
     kokona
    1.37
     completamente
    1.36
    entire
    1.30
    Activations Density 0.584%

    No Known Activations