Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7522
    Prev
    Next
    INDEX
    Explanations

    strings and string-related functions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gyhoeddwyd
    -0.64
     незавершена
    -0.63
    AndEndTag
    -0.62
    agonal
    -0.59
    참고
    -0.57
    dues
    -0.56
    =-=-=-=-
    -0.56
     CreateTagHelper
    -0.55
    apsed
    -0.55
    __(/*!
    -0.55
    POSITIVE LOGITS
     str
    1.93
    str
    1.79
     Str
    1.61
    Str
    1.57
     STR
    1.26
    STR
    1.23
     Strath
    0.91
     Stroud
    0.85
    strs
    0.84
     strs
    0.82
    Activations Density 0.064%

    No Known Activations