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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 2836
    Prev
    Next
    INDEX
    Explanations

    terms related to the act of adopting or adoption in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    centerX
    -0.71
    VersionUID
    -0.70
     Baumann
    -0.67
    PageInfo
    -0.67
    centerY
    -0.66
    BeforeAll
    -0.66
    bindParam
    -0.66
     Springsteen
    -0.64
     млн
    -0.63
     gql
    -0.63
    POSITIVE LOGITS
     Adop
    2.04
     adoption
    1.93
     adop
    1.90
    Adop
    1.90
     adopted
    1.82
     adopting
    1.78
     adopts
    1.78
     Adopt
    1.78
     Adoption
    1.77
     adopt
    1.74
    Activations Density 0.059%

    No Known Activations