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. 18-GEMMASCOPE-RES-16K
    6. 529
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns indicating specific references

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

    Sentences following "that" or "this"

    np_acts-logits-general · gemini-2.0-flash

    referring to something

    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
     betreft
    -0.61
     riuscito
    -0.57
    seamnă
    -0.57
     precedes
    -0.50
    SizeMode
    -0.49
     refere
    -0.46
    urlopen
    -0.46
     resembles
    -0.46
     rör
    -0.45
    례
    -0.45
    POSITIVE LOGITS
     चीज़ों
    0.75
     stuff
    0.72
     situation
    0.63
     particular
    0.63
    rungsseite
    0.63
    ,))
    0.61
    bewerken
    0.60
    situation
    0.60
    IntoConstraints
    0.60
     thing
    0.60
    Activations Density 0.223%

    No Known Activations