Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 12681
    Prev
    Next
    INDEX
    Explanations

    terms related to sodium chloride and its effects

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

    Salt or sodium chloride (NaCl)

    np_acts-logits-general · gemini-2.0-flash

    salt or NaCl challenge

    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
     Hend
    -0.59
    Hend
    -0.57
     Hout
    -0.55
     Brennan
    -0.55
     Jimi
    -0.54
     Kendrick
    -0.54
     Arag
    -0.54
     LOGGER
    -0.53
     McCa
    -0.52
    Aub
    -0.51
    POSITIVE LOGITS
    Sal
    2.70
     salt
    2.66
     Sal
    2.65
     SAL
    2.64
     sal
    2.58
    sal
    2.54
     Salt
    2.52
    SAL
    2.44
    Salt
    2.40
    salt
    2.40
    Activations Density 0.284%

    No Known Activations