© 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. 35-GEMMASCOPE-RES-16K
    11. 6646
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts, particularly in relation to data structures and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     esternos
    -0.66
     للاسماء
    -0.60
     فريبيس
    -0.59
     surla
    -0.54
    ᅠ
    -0.54
    存于互联网档案馆
    -0.52
    PyExc
    -0.51
    DebuggerStep
    -0.51
     AssemblyProduct
    -0.50
    IndentedString
    -0.50
    POSITIVE LOGITS
     Perl
    0.40
    push
    0.38
     POD
    0.38
    perl
    0.38
    undef
    0.38
    推
    0.37
     push
    0.36
    pod
    0.35
     undef
    0.35
     scalar
    0.35
    Activations Density 0.213%

    No Known Activations