© 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. 22-GEMMASCOPE-RES-16K
    6. 15347
    Prev
    Next
    INDEX
    Explanations

    expressions indicating degree or intensity

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

    Follows "very" or "more."

    np_acts-logits-general · gemini-2.0-flash

    intensifiers followed by descriptors

    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
    abinieri
    -0.52
     InputDecoration
    -0.52
     picioare
    -0.51
     devrez
    -0.51
     extérieures
    -0.51
     tasche
    -0.51
     malheure
    -0.50
     noires
    -0.50
     piele
    -0.49
     decidedly
    -0.49
    POSITIVE LOGITS
     matured
    0.73
    __(/*!
    0.73
     Administrativna
    0.70
    ########.
    0.67
    MENAFN
    0.66
     secured
    0.65
    justed
    0.64
     createState
    0.64
    RTCK
    0.63
     otomatig
    0.61
    Activations Density 0.278%

    No Known Activations