© 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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 10888
    Prev
    Next
    INDEX
    Explanations

    elements related to educational resources and materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uitz
    -0.47
    intervento
    -0.44
     droog
    -0.40
    RectangleBorder
    -0.40
     żyw
    -0.39
     vectoriales
    -0.39
    insegna
    -0.35
    campal
    -0.34
     wensen
    -0.34
     mattino
    -0.34
    POSITIVE LOGITS
    RegistryLite
    0.53
    zzleHttp
    0.52
     utafitiHapana
    0.51
     dAtA
    0.50
     defStyle
    0.49
    PyExc
    0.49
     nakalista
    0.47
    parsedMessage
    0.47
    BagConstraints
    0.45
    ItemLayout
    0.45
    Activations Density 0.796%

    No Known Activations