© 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. 7-GEMMASCOPE-RES-16K
    11. 4239
    Prev
    Next
    INDEX
    Explanations

    mentions of specific software libraries or frameworks

    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
    ValueStyle
    -1.23
    ConstraintMaker
    -0.89
    EndInit
    -0.79
    bootstrapcdn
    -0.78
    AndEndTag
    -0.77
    mybatisplus
    -0.73
    Hochspringen
    -0.73
     AppCompatTheme
    -0.72
    LayoutStyle
    -0.71
     CreateTagHelper
    -0.70
    POSITIVE LOGITS
    DoubleQuotes
    1.65
     BoxDecoration
    1.24
    VersionUID
    1.12
    AppCompat
    0.92
    ViewHolder
    0.84
     оригіналу
    0.72
    IContainer
    0.58
     Дата
    0.57
    RestController
    0.57
     autón
    0.56
    Activations Density 0.006%

    No Known Activations