© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 10578
    Prev
    Next
    INDEX
    Explanations

    themes related to personal growth and transformative experiences

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

    "it" followed by a past tense verb

    np_acts-logits-general · gemini-2.0-flash

    teaching about its effects or changes

    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
    twimg
    -0.59
    apunov
    -0.54
     pulumi
    -0.51
    typeorm
    -0.50
    afficheront
    -0.50
     turísticos
    -0.50
    pyx
    -0.49
    nå
    -0.48
    Referencie
    -0.47
    álva
    -0.46
    POSITIVE LOGITS
     taught
    1.32
     teach
    1.13
     teaches
    1.05
     Taught
    1.04
    taught
    0.97
     teaching
    0.95
     Teach
    0.94
    teach
    0.88
    Teach
    0.85
     Teaching
    0.83
    Activations Density 0.245%

    No Known Activations