© 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. 12-GEMMASCOPE-RES-16K
    11. 3163
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate composition or the makeup of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ironically
    -0.43
     jadx
    -0.40
    URLConnection
    -0.39
    pyrid
    -0.39
    errHandler
    -0.38
     obliquely
    -0.38
     threatened
    -0.38
     späteren
    -0.36
     pinulongan
    -0.36
    later
    -0.36
    POSITIVE LOGITS
     consists
    1.40
     consisted
    1.38
     comprised
    1.33
     consisting
    1.32
     consist
    1.23
     comprises
    1.23
     comprising
    1.20
     composed
    1.19
     comprise
    1.17
     består
    1.13
    Activations Density 0.433%

    No Known Activations