© 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. 16-GEMMASCOPE-RES-16K
    11. 1167
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to chemical reactions and industrial manufacturing

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

    Text related to chemical processes or materials

    np_acts-logits-general · gemini-2.0-flash

    powder, material, ion, gas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.51
    guer
    -0.48
    ands
    -0.46
     zeker
    -0.46
    aud
    -0.46
    buah
    -0.45
    çek
    -0.44
     noqa
    -0.43
    versus
    -0.43
    compared
    -0.42
    POSITIVE LOGITS
    Personendaten
    0.86
     <=",
    0.81
     newly
    0.71
    abestanden
    0.70
     newfound
    0.69
    labelledby
    0.68
     <",
    0.67
    GenerationType
    0.65
    Autoritní
    0.64
     acquired
    0.63
    Activations Density 0.937%

    No Known Activations