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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 808
    Prev
    Next
    INDEX
    Explanations

    structural elements related to code and programming functions

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

    Tree structures: parent, child, levels

    np_acts-logits-general · gemini-2.0-flash

    hierarchical tree structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arden
    -0.48
     repur
    -0.45
    ecap
    -0.42
    DataColumn
    -0.41
    xnn
    -0.41
     junho
    -0.41
     cape
    -0.41
    AutoField
    -0.40
     Cape
    -0.39
     שוליים
    -0.39
    POSITIVE LOGITS
     tree
    1.32
     subtree
    1.27
     Tree
    1.22
     recursively
    1.21
    Tree
    1.19
     TREE
    1.15
    tree
    1.13
     parent
    1.13
     recursive
    1.10
    TREE
    1.08
    Activations Density 0.920%

    No Known Activations