© 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-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2169
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and company affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recommandons
    -0.42
    WebElementEntity
    -0.38
     dė
    -0.37
     refirió
    -0.34
    WebpackPlugin
    -0.34
     carriera
    -0.32
     refiere
    -0.32
     concursos
    -0.32
     vuestro
    -0.32
     thérape
    -0.31
    POSITIVE LOGITS
     headquartered
    0.69
     headquarters
    0.61
    Portail
    0.61
    总部
    0.56
    Headquarters
    0.56
    的公司
    0.54
    quartered
    0.54
    EndInit
    0.53
     empresa
    0.52
     Headquarters
    0.51
    Activations Density 0.278%

    No Known Activations