© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6463
    Prev
    Next
    INDEX
    Explanations

    instances of a specific identifier or code within a dataset

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     isComment
    -0.41
    citos
    -0.40
    
    -0.38
    ngiliz
    -0.38
    pherals
    -0.36
    ogly
    -0.36
     AppCompatTheme
    -0.36
    tedra
    -0.35
    naje
    -0.35
    temos
    -0.35
    POSITIVE LOGITS
    ca
    3.08
     ca
    2.50
    CA
    1.96
     CA
    1.77
     Ca
    1.74
    Ca
    1.71
    cae
    1.02
    caj
    0.95
     caul
    0.94
    caa
    0.93
    Activations Density 0.694%

    No Known Activations