© 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. 24-GEMMASCOPE-RES-16K
    11. 12517
    Prev
    Next
    INDEX
    Explanations

    any mention of change or variations in different contexts

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

    "Change" and its variations

    np_acts-logits-general · gemini-2.0-flash

    change followed by specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.53
    tdessen
    -0.48
    closedir
    -0.47
    WritableDatabase
    -0.45
    viewtopic
    -0.45
    rowData
    -0.45
    fclose
    -0.45
     تانيه
    -0.44
    attenzione
    -0.44
    unehmen
    -0.43
    POSITIVE LOGITS
    over
    0.84
     Change
    0.77
     apport
    0.76
    changing
    0.75
    transQ
    0.75
    Changing
    0.75
     Changing
    0.75
     change
    0.74
     changing
    0.74
     changer
    0.72
    Activations Density 0.183%

    No Known Activations