© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 17737
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal statements and expressions of individual experiences

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

    technical or procedural descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    LookAnd
    -0.85
    yntaxException
    -0.81
     Administrativna
    -0.71
     PeEnEo
    -0.68
     صوتيه
    -0.67
     externi
    -0.62
     uVar
    -0.60
    AndroidJUnit
    -0.60
     мәкал
    -0.60
    IntoConstraints
    -0.60
    POSITIVE LOGITS
     leiding
    0.30
    دور
    0.29
    inferior
    0.27
    ธิ
    0.26
    plural
    0.26
     skriv
    0.26
    daniel
    0.25
    unknownFields
    0.25
    ('-'
    0.25
     <<<<<<<<<<<<<<
    0.25
    Activations Density 0.050%

    No Known Activations