© 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. 11271
    Prev
    Next
    INDEX
    Explanations

    phrases related to knowledge, identification, and questioning

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

    "who" or similar pronouns

    np_acts-logits-general · gemini-2.0-flash

    identifying who

    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
     nahilalakip
    -0.85
    fjspx
    -0.58
     CURIAM
    -0.55
    دانشنامهٔ
    -0.54
    EDEFAULT
    -0.54
    withstanding
    -0.54
    rativa
    -0.53
    θηκαν
    -0.51
    IVEREF
    -0.50
    SharedCtor
    -0.49
    POSITIVE LOGITS
     who
    3.69
    who
    3.16
     Who
    2.90
    Who
    2.90
     quién
    2.49
     whom
    2.37
     hvem
    2.37
     quien
    2.36
    WHO
    2.16
     siapa
    2.10
    Activations Density 0.365%

    No Known Activations