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. 10315
    Prev
    Next
    INDEX
    Explanations

    references to possession or ownership

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

    Perfect tense auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    have + past participle

    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
    ]")]
    -0.65
    setVerticalGroup
    -0.65
    CompilerServices
    -0.60
    itness
    -0.53
    Formazione
    -0.50
    ∭
    -0.49
    envolvimento
    -0.48
    ようになる
    -0.46
    Наде
    -0.46
    ⛈
    -0.46
    POSITIVE LOGITS
     been
    2.36
     gotten
    1.97
    been
    1.81
     gone
    1.75
     BEEN
    1.50
     taken
    1.49
     undergone
    1.48
     got
    1.47
     begun
    1.42
     Been
    1.41
    Activations Density 0.628%

    No Known Activations