Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12840
    Prev
    Next
    INDEX
    Explanations

    phrases related to internal connections in various contexts

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

    Followed by "house," "depth," or "person."

    np_acts-logits-general · gemini-2.0-flash

    in-depth, in-house, in-person, in-studio

    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
    astéroïdes
    -0.68
     VIAF
    -0.65
    الدراسه
    -0.64
    RegistryLite
    -0.64
    usters
    -0.62
    istoitu
    -0.61
    Становништво
    -0.61
     الحره
    -0.61
    lishes
    -0.60
    bardier
    -0.59
    POSITIVE LOGITS
     house
    0.80
    house
    0.74
    -
    0.60
    depth
    0.59
     House
    0.57
    person
    0.55
    House
    0.54
     person
    0.54
     HOUSE
    0.53
     depth
    0.53
    Activations Density 0.131%

    No Known Activations