© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12883
    Prev
    Next
    INDEX
    Explanations

    specific terms related to technical features and processes in technology and finance

    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
     disambiguazione
    -0.62
     betweenstory
    -0.52
    StoryboardSegue
    -0.49
     utafitiHapana
    -0.48
    akterysty
    -0.42
    Filmografie
    -0.40
     ujednoznacz
    -0.38
     defaultstate
    -0.37
    Aktualisiert
    -0.36
     AttributeSet
    -0.35
    POSITIVE LOGITS
    tagHelperRunner
    0.51
    GrantedAuthority
    0.47
    principalColumn
    0.46
    IDC
    0.45
    iſen
    0.44
    fjspx
    0.43
     BoxFit
    0.43
    Šaltiniai
    0.43
    PYX
    0.43
     gods
    0.43
    Activations Density 0.305%

    No Known Activations