Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105149
    Prev
    Next
    INDEX
    Explanations

    elements related to public health studies and data analysis

    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
     setUser
    -0.35
     Tom
    -0.34
    Emo
    -0.34
     defa
    -0.34
    Wo
    -0.34
    wohl
    -0.34
    msch
    -0.33
    Embeddable
    -0.33
     news
    -0.33
     press
    -0.33
    POSITIVE LOGITS
    addGap
    0.60
    Personendaten
    0.60
    +#+
    0.58
    }>;
    0.55
    HostException
    0.55
     مشين
    0.54
     contemporáneo
    0.51
     CURIAM
    0.50
    SBATCH
    0.50
     Италијани
    0.50
    Activations Density 0.015%

    No Known Activations