© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 16377
    Prev
    Next
    INDEX
    Explanations

    instructions or steps related to processes or guidelines

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

    Preceding guidance-related words

    np_acts-logits-general · gemini-2.0-flash

    following instructions

    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
     resourceCulture
    -0.73
    djangoproject
    -0.63
    Према
    -0.58
     Palmas
    -0.56
     Quo
    -0.56
     cherchés
    -0.55
    想想
    -0.54
     مرئيه
    -0.54
    SharedDtor
    -0.53
     joaat
    -0.51
    POSITIVE LOGITS
     instructions
    2.33
     instruction
    2.00
     Instructions
    1.91
    instructions
    1.89
    Instructions
    1.81
     directions
    1.75
    instruction
    1.70
     INSTRUCTIONS
    1.69
     Instruction
    1.65
     tutorial
    1.65
    Activations Density 0.499%

    No Known Activations