© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14826
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and contractual language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns and named entities, particularly person names and organization names.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Milán
    -0.45
     Argentino
    -0.40
     Holanda
    -0.38
     Masyarakat
    -0.37
    }}}}
    -0.35
     Eropa
    -0.35
     Ekonomi
    -0.35
     miniatura
    -0.34
     Utama
    -0.34
     Prata
    -0.33
    POSITIVE LOGITS
    ſelben
    0.76
    iſen
    0.71
    iſten
    0.65
    ؤلاء
    0.64
    EndContext
    0.64
     laſſen
    0.63
    ogast
    0.63
    AddTagHelper
    0.63
    ohyd
    0.61
     pulumi
    0.61
    Activations Density 0.758%

    No Known Activations