© 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. 5-GEMMASCOPE-RES-16K
    11. 7085
    Prev
    Next
    INDEX
    Explanations

    code structure components, particularly related to graphical user interface elements and programming references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.96
    tagHelperRunner
    -0.76
    ViewFeatures
    -0.75
    帖最后由
    -0.66
     onCreateView
    -0.63
     lenker
    -0.61
    AddTagHelper
    -0.60
    AndEndTag
    -0.60
    MessageTagHelper
    -0.58
    SourceChecksum
    -0.57
    POSITIVE LOGITS
    arXiv
    1.32
     cref
    1.21
    multirow
    0.90
    ########.
    0.85
    $_['
    0.78
    badlogic
    0.75
    HasColumnType
    0.75
    amazonaws
    0.69
    bukkit
    0.68
    GrantedAuthority
    0.65
    Activations Density 0.014%

    No Known Activations