© 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-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7811
    Prev
    Next
    INDEX
    Explanations

    programming code components related to Android development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.91
     محفوظة
    -0.76
     AssemblyCompany
    -0.70
     AssemblyCulture
    -0.70
    ApiModelProperty
    -0.69
     queſta
    -0.68
    ſſung
    -0.68
     beginnetje
    -0.67
     Italijanski
    -0.67
    Попис
    -0.67
    POSITIVE LOGITS
    import
    1.02
     import
    0.66
     incluida
    0.36
     importar
    0.36
     including
    0.35
     orgánico
    0.33
    using
    0.33
    以及
    0.33
     into
    0.32
    from
    0.32
    Activations Density 0.055%

    No Known Activations