© 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. 18-GEMMASCOPE-RES-16K
    6. 6837
    Prev
    Next
    INDEX
    Explanations

    dialogue elements and conversational exchanges

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

    Confirmation or affirmation words (yes, absolutely)

    np_acts-logits-general · gemini-2.0-flash

    agreement or confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.75
     prochains
    -0.61
    ]='\
    -0.57
    Portail
    -0.55
    |<\
    -0.53
    исленность
    -0.50
    ngOnInit
    -0.46
    ξεις
    -0.46
    שב
    -0.46
     Roskov
    -0.45
    POSITIVE LOGITS
     absolutely
    0.99
    Absolutely
    0.96
     Absolutely
    0.93
    absolutely
    0.81
    Yes
    0.79
     assolutamente
    0.76
     Yes
    0.76
     dAtA
    0.76
     absolument
    0.76
     yes
    0.75
    Activations Density 0.144%

    No Known Activations