© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12481
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers incremented by 1

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1343
    +0.20
    0.6%
    674
    +0.19
    0.6%
    1108
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1108
    +0.20
    0.03
    1900
    +0.19
    0.02
    1216
    +0.12
    0.03
    Negative Logits
     للتو
    -0.65
    Życiorys
    -0.60
    scienced
    -0.58
    jRadioButton
    -0.58
    Veel
    -0.57
    Biografía
    -0.57
    Flere
    -0.57
    Apenas
    -0.56
    Dzi
    -0.56
    Från
    -0.56
    POSITIVE LOGITS
     fluo
    1.24
     ù
    1.10
     dì
    1.08
     haup
    1.04
     bordeaux
    1.02
     eyel
    0.99
     vhs
    0.95
     peppa
    0.95
     oreo
    0.95
     baf
    0.95
    Activations Density 0.059%

    No Known Activations