© 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. 5669
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or importance in various contexts

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

    "Of" followed by importance, concern, interest

    np_acts-logits-general · gemini-2.0-flash

    matters of import or interest

    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
    WriteTagHelper
    -0.90
    IsContent
    -0.84
     '\\;'
    -0.84
    
    -0.82
    Geplaatst
    -0.79
     AssemblyVersion
    -0.77
     AssemblyCulture
    -0.77
    OGND
    -0.76
    fjspx
    -0.75
    __':
    -0.75
    POSITIVE LOGITS
     great
    2.19
    great
    1.72
     greater
    1.65
     considerable
    1.63
     greatest
    1.58
     tremendous
    1.58
     immense
    1.42
     significant
    1.36
     enormous
    1.35
    greatest
    1.32
    Activations Density 0.783%

    No Known Activations