© 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. 9638
    Prev
    Next
    INDEX
    Explanations

    discussions related to iron and its role in biological processes

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

    Mitochondrial electron transport chain

    np_acts-logits-general · gemini-2.0-flash

    mitochondrial electron transport

    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
     يتيمه
    -0.68
     Wake
    -0.53
    UserScript
    -0.51
    civil
    -0.49
    AutoScale
    -0.49
    DockStyle
    -0.48
    Wake
    -0.48
     CWE
    -0.47
    harma
    -0.47
    cuerdo
    -0.46
    POSITIVE LOGITS
     mitochondrial
    0.79
     cytochrome
    0.77
     redox
    0.76
     mitochondria
    0.73
     NAD
    0.71
     Mitochondrial
    0.69
    NAD
    0.68
     Mitochond
    0.68
     oxygen
    0.68
     dehydrogenase
    0.66
    Activations Density 0.952%

    No Known Activations