© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1486
    Prev
    Next
    INDEX
    Explanations

    comment blocks in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     సౌకర్య
    -0.67
     BoxFit
    -0.66
     Normdatei
    -0.63
     newBuilder
    -0.60
    ="+
    -0.58
     and
    -0.56
     ComVisible
    -0.55
    rootDir
    -0.55
    eb
    -0.55
    enden
    -0.55
    POSITIVE LOGITS
    /*
    1.58
    /*
    1.19
    (/*
    1.07
     /*
    0.91
     OMITBAD
    0.87
    __(/*!
    0.83
     ${({
    0.82
     fertiliser
    0.82
    +/*
    0.82
    SpringBootTest
    0.81
    Activations Density 0.103%

    No Known Activations