© 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. 9-GEMMASCOPE-RES-16K
    6. 15938
    Prev
    Next
    INDEX
    Explanations

    events or announcements regarding memorial services and funerals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.58
     виправивши
    -0.57
    исленность
    -0.52
    pcap
    -0.51
    ########.
    -0.49
     âgées
    -0.49
    fetchall
    -0.48
     Ucraina
    -0.48
     HasFactory
    -0.47
     Fiche
    -0.46
    POSITIVE LOGITS
     intptr
    0.67
    PositiveButton
    0.65
    Personendaten
    0.64
     الحره
    0.63
    ClientSize
    0.59
    basicConfig
    0.59
     Audiodateien
    0.57
    CrossOrigin
    0.56
    XmlRootElement
    0.54
    swell
    0.54
    Activations Density 0.019%

    No Known Activations