© 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. 10094
    Prev
    Next
    INDEX
    Explanations

    references to educational qualifications and credentials

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

    teaching or teachers

    np_acts-logits-general · gemini-2.0-flash

    people who teach and educate

    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
    mspace
    -0.64
    Executives
    -0.61
    /******/
    -0.60
     COO
    -0.58
    tadiene
    -0.56
    TypedDataSet
    -0.56
     дописавши
    -0.54
    ganet
    -0.54
     spina
    -0.52
     Unmarshal
    -0.49
    POSITIVE LOGITS
     teaching
    2.46
     teach
    2.23
     Teaching
    2.19
    Teaching
    2.10
    teaching
    2.07
     teacher
    2.05
     TEACHING
    1.94
     Teach
    1.90
     teachers
    1.85
     teaches
    1.84
    Activations Density 0.210%

    No Known Activations