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. 7-GEMMASCOPE-RES-16K
    6. 15777
    Prev
    Next
    INDEX
    Explanations

    references to "forking" and tree-related structures 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 @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.57
    __':
    -0.55
    angliski
    -0.44
    djangoproject
    -0.43
     Italijanski
    -0.43
     snippetHide
    -0.40
     nød
    -0.40
    __":
    -0.39
    wußt
    -0.39
    теризу
    -0.38
    POSITIVE LOGITS
     fork
    1.58
     forks
    1.38
    fork
    1.38
    Fork
    1.27
     forked
    1.25
     Fork
    1.24
    forks
    1.19
     branching
    1.13
     divergence
    1.00
     bifurcation
    1.00
    Activations Density 0.492%

    No Known Activations