© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2635
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Str" and its variations in various contexts, likely related to software or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.50
    AddTagHelper
    -0.48
     Vikipedi
    -0.46
    ädie
    -0.43
    IVersion
    -0.43
    Elmer
    -0.42
    Gön
    -0.42
     defaultstate
    -0.42
     CreateTagHelper
    -0.41
    DockStyle
    -0.41
    POSITIVE LOGITS
     Str
    2.55
    STR
    2.50
     STR
    2.48
    Str
    2.39
     Stra
    2.33
     str
    2.30
    str
    2.23
    stra
    2.20
    Stra
    2.19
     stra
    2.02
    Activations Density 0.177%

    No Known Activations