© 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. 22-GEMMASCOPE-RES-16K
    11. 10683
    Prev
    Next
    INDEX
    Explanations

    metabolite analysis and characterization through mass spectrometry data

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

    Prepositions/symbols followed by mass spectrometry terms

    np_acts-logits-general · gemini-2.0-flash

    mass spectrometry analysis

    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
    ValueStyle
    -0.60
    Referências
    -0.58
    ########.
    -0.58
    EndContext
    -0.57
    EndInit
    -0.57
     esternos
    -0.56
    __*/
    -0.53
    ագրություններ
    -0.53
     estekak
    -0.52
    Demografía
    -0.49
    POSITIVE LOGITS
     mass
    0.93
     fragmentation
    0.91
     Mass
    0.83
    Mass
    0.83
     Fragment
    0.80
    mass
    0.80
     ionization
    0.78
    Caprio
    0.77
     fragment
    0.75
     MASS
    0.73
    Activations Density 0.661%

    No Known Activations