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. 7-GEMMASCOPE-RES-16K
    6. 4580
    Prev
    Next
    INDEX
    Explanations

    terms related to legitimacy and citizenship issues regarding children born outside of marriage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sanitarios
    -0.50
    gebob
    -0.49
     kulit
    -0.47
    řízení
    -0.47
     Zeichen
    -0.47
     sanitarias
    -0.43
     extensão
    -0.43
     locali
    -0.43
    Tell
    -0.43
     shortness
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.72
     ProtoMessage
    0.71
     begotten
    0.66
    Jereo
    0.66
     StringTokenizer
    0.65
    HideFlags
    0.64
    tvguidetime
    0.63
     paternity
    0.62
     parentage
    0.61
    CopyWith
    0.61
    Activations Density 0.203%

    No Known Activations