© 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. 12-GEMMASCOPE-RES-16K
    11. 5819
    Prev
    Next
    INDEX
    Explanations

    numerical values and symbols related to data representations or mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conſ
    -0.66
     ſur
    -0.61
    AddTagHelper
    -0.61
     ſta
    -0.58
     ſche
    -0.58
    ngrx
    -0.57
     ſever
    -0.56
     ſch
    -0.55
     AssemblyCompany
    -0.55
     оригіналу
    -0.55
    POSITIVE LOGITS
     setuptools
    0.36
    否
    0.35
    Eben
    0.34
    icitis
    0.33
     Tens
    0.33
    󠁬
    0.32
    Tens
    0.32
     contextLoads
    0.32
     ком
    0.32
    lič
    0.32
    Activations Density 1.077%

    No Known Activations