© 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. 12579
    Prev
    Next
    INDEX
    Explanations

    phrases related to existential themes and life transitions

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

    Past tense narrative context

    np_acts-logits-general · gemini-2.0-flash

    conflict and violence

    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
    hoodie
    -0.48
     basic
    -0.48
    jangkau
    -0.48
    larg
    -0.47
    抑
    -0.47
    تاح
    -0.46
    基本
    -0.46
    ocusing
    -0.46
     focus
    -0.45
    AddRange
    -0.45
    POSITIVE LOGITS
     villagers
    0.91
     village
    0.83
     villages
    0.77
     messengers
    0.72
     villager
    0.71
     whereupon
    0.69
     frightened
    0.69
     travellers
    0.68
     effray
    0.65
    village
    0.64
    Activations Density 0.411%

    No Known Activations