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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 501
    Prev
    Next
    INDEX
    Explanations

    the presence of names or initials, indicative of authors or contributors in a scientific context

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

    initials following first name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     tartalomajánló
    -0.85
    Personendaten
    -0.74
    majánló
    -0.73
     ligiloj
    -0.69
    XmlAccessType
    -0.68
    ðsíða
    -0.63
    niksi
    -0.63
     ProtoMessage
    -0.61
     nakalista
    -0.61
    Хьажоргаш
    -0.61
    POSITIVE LOGITS
     betweenstory
    0.35
    ifikant
    0.27
     Jr
    0.27
    artige
    0.24
    DG
    0.23
     faut
    0.23
    tudo
    0.23
    bcryptjs
    0.23
    ínű
    0.23
     intptr
    0.22
    Activations Density 0.080%

    No Known Activations