© 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. 22-GEMMASCOPE-RES-16K
    11. 6490
    Prev
    Next
    INDEX
    Explanations

    instances of methods and functions related to string manipulation and data splitting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mes
    -0.27
     yh
    -0.27
     empty
    -0.26
    Empty
    -0.26
    doctype
    -0.25
    inheritdoc
    -0.25
    怎样
    -0.24
    แก่
    -0.24
     Paterson
    -0.24
    include
    -0.24
    POSITIVE LOGITS
     GenerationType
    0.82
     StringTokenizer
    0.79
    yntaxException
    0.77
     فريبيس
    0.72
    CppMethod
    0.71
    AxisAlignment
    0.69
    NameInMap
    0.68
    FieldBuilder
    0.67
    GOTREF
    0.66
     Split
    0.65
    Activations Density 0.151%

    No Known Activations