© 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. 18-GEMMASCOPE-RES-16K
    11. 2680
    Prev
    Next
    INDEX
    Explanations

    pharmaceutical and biochemical terms related to pH and buffering solutions

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

    pH

    np_acts-logits-general · gemini-2.0-flash

    pH followed by numbers

    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
    WriteBarrier
    -0.70
     nahilalakip
    -0.59
     makeStyles
    -0.58
    GoogleApiClient
    -0.57
     Satellite
    -0.57
    WithIdentifier
    -0.56
    ollectionView
    -0.55
     Reverso
    -0.54
    éndolo
    -0.53
     eventdata
    -0.53
    POSITIVE LOGITS
     pH
    1.77
    pH
    1.55
     acidity
    1.13
     acidic
    1.12
     Acid
    1.08
     acid
    1.07
    Acid
    1.02
    acid
    0.98
     ACID
    0.92
     alkaline
    0.87
    Activations Density 0.403%

    No Known Activations