© 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. 16-GEMMASCOPE-RES-16K
    11. 13204
    Prev
    Next
    INDEX
    Explanations

    references to resource identifiers in a coding context, particularly in Android development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     theore
    -0.41
    цездатний
    -0.40
    WithMany
    -0.39
    ecycle
    -0.39
     rural
    -0.37
     sustain
    -0.37
     oprot
    -0.37
     Theore
    -0.36
    OneToOne
    -0.36
     HttpHeaders
    -0.36
    POSITIVE LOGITS
    AccessorTable
    0.56
    ffindor
    0.56
     IBOutlet
    0.56
    styleable
    0.55
     StyleSheet
    0.55
    IBOutlet
    0.54
     aapt
    0.52
     drawable
    0.52
    RTSN
    0.52
    WebElementEntity
    0.52
    Activations Density 0.028%

    No Known Activations