© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6279
    Prev
    Next
    INDEX
    Explanations

    concepts related to structural remedies in organizational settings

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

    splitting or dividing

    np_acts-logits-general · gemini-2.0-flash

    dividing into parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    backends
    -0.55
    styleType
    -0.54
    RegistryLite
    -0.53
    Tikang
    -0.52
    Démographie
    -0.51
    échal
    -0.51
     باخ
    -0.50
     étrangère
    -0.49
     "..\..\
    -0.48
    providedIn
    -0.48
    POSITIVE LOGITS
     split
    3.12
     splitting
    2.75
     Split
    2.73
     splits
    2.68
     divide
    2.67
    split
    2.64
    Split
    2.64
     divided
    2.63
     divides
    2.50
     dividing
    2.44
    Activations Density 1.076%

    No Known Activations