© 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. 9131
    Prev
    Next
    INDEX
    Explanations

    references to criteria or evaluations based on guidelines or assessments

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

    Following "on" or "upon"

    np_acts-logits-general · gemini-2.0-flash

    based on assumptions or facts

    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
     anlam
    -0.58
     manières
    -0.54
    Remedy
    -0.52
    TagMode
    -0.52
     inneces
    -0.51
     ogóle
    -0.49
    …………………………………………
    -0.48
    endphp
    -0.48
    endl
    -0.47
    UnsafeEnabled
    -0.47
    POSITIVE LOGITS
     principles
    0.83
     assumption
    0.83
     observations
    0.81
     considerations
    0.80
     assumptions
    0.79
     criteria
    0.76
     recommendations
    0.74
     feedback
    0.72
    principles
    0.71
     findings
    0.71
    Activations Density 0.595%

    No Known Activations