© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6205
    Prev
    Next
    INDEX
    Explanations

    phrases related to digital advertising and its various channels

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

    Connectives: "via", "through", "as", "on", "or"

    np_acts-logits-general · gemini-2.0-flash

    communication via various mediums

    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
     Administrativna
    -0.62
     userSchema
    -0.57
     kasarigan
    -0.53
    esModule
    -0.52
    +#+#
    -0.51
    Jîn
    -0.49
    matchCondition
    -0.48
    InvalidProtocol
    -0.48
    AndEndTag
    -0.48
     ***!
    -0.48
    POSITIVE LOGITS
     telephone
    1.06
     phone
    1.04
     email
    1.04
     physical
    0.95
     smartphone
    0.92
     traditional
    0.88
     SMS
    0.88
     fax
    0.87
     newspaper
    0.83
     web
    0.82
    Activations Density 0.473%

    No Known Activations