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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7466
    Prev
    Next
    INDEX
    Explanations

    structural elements of HTML and their associated classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewUrlParser
    -0.65
    }*/
    
    -0.64
    IsContent
    -0.63
    SourceChecksum
    -0.53
    ?}
    -0.53
     chromium
    -0.53
    niſſe
    -0.52
     Stub
    -0.52
    }*/
    -0.51
    fjspx
    -0.51
    POSITIVE LOGITS
    <
    0.53
    <!--
    0.45
     Desenvolvimento
    0.42
     Comunicação
    0.41
     navideña
    0.40
     sección
    0.40
     húmedo
    0.40
     verrez
    0.39
     nocturno
    0.38
    </
    0.38
    Activations Density 0.058%

    No Known Activations