© 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. 5618
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the degree of proximity or likelihood, particularly words like "almost."

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

    following "almost"

    np_acts-logits-general · gemini-2.0-flash

    near absolute quantification

    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
     وتسجيلات
    -0.73
    SBATCH
    -0.63
     AssemblyTitle
    -0.61
    seamnă
    -0.59
     հղումներ
    -0.58
    بوابة
    -0.56
     विश्वसनीयता
    -0.55
     Lordships
    -0.53
     cref
    -0.53
    లాలు
    -0.52
    POSITIVE LOGITS
     exclusively
    0.83
     identical
    0.82
     certainly
    0.80
     impossible
    0.75
     entirely
    0.72
     imperceptible
    0.72
     universally
    0.68
     nothing
    0.68
     always
    0.66
     Certainly
    0.66
    Activations Density 0.116%

    No Known Activations