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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9246
    Prev
    Next
    INDEX
    Explanations

    various list operations and manipulations in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    variable assignment operations using the equals sign.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.32
     GlobalKey
    -0.30
    Queues
    -0.30
    FDRE
    -0.29
    PC
    -0.29
    credits
    -0.29
    GC
    -0.28
     دان
    -0.28
    startswith
    -0.27
     over
    -0.27
    POSITIVE LOGITS
     betweenstory
    0.83
     Walkover
    0.59
     AssemblyCompany
    0.59
    期刊论文
    0.58
     collectively
    0.58
     jotka
    0.58
    =[]
    0.56
    rungsseite
    0.55
     CallOverrides
    0.55
     dAtA
    0.54
    Activations Density 0.260%

    No Known Activations