© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105627
    Prev
    Next
    INDEX
    Explanations

    special characters, particularly structural elements used in programming or formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     magasiner
    -0.56
     enjoyment
    -0.54
     Cuen
    -0.52
     sánchez
    -0.51
     noël
    -0.50
     protection
    -0.50
     defenses
    -0.50
    tinyos
    -0.50
     lópez
    -0.50
     battles
    -0.49
    POSITIVE LOGITS
    |}
    1.05
    ||}
    0.64
    |}\
    0.64
    Personensuche
    0.63
    SequentialGroup
    0.59
     <<<<<<<<<<<<<<
    0.57
     AssemblyTitle
    0.54
     ***!
    0.51
    })*/
    0.49
    \{\\
    0.49
    Activations Density 0.001%

    No Known Activations