© 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. 2-GEMMASCOPE-RES-16K
    11. 5666
    Prev
    Next
    INDEX
    Explanations

    the presence of terms related to alternatives or alternate options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     препратки
    -0.59
     Meksiku
    -0.55
     AssemblyCompany
    -0.47
    principalColumn
    -0.47
    RODU
    -0.44
    <?
    -0.44
    humanité
    -0.43
     CHAIR
    -0.43
    lineHeight
    -0.43
     BorderRadius
    -0.42
    POSITIVE LOGITS
     alternate
    1.30
     altern
    1.27
    altern
    1.25
    Altern
    1.20
     Altern
    1.17
    alternate
    1.15
     alternates
    1.13
     alternating
    1.09
    Alternate
    1.08
     Alternate
    1.08
    Activations Density 0.140%

    No Known Activations