© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15180
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes or steps in a sequence

    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
    1937
    +0.20
    0.7%
    50
    +0.15
    0.6%
    478
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1937
    +0.20
    0.11
    862
    +0.15
    0.06
    478
    +0.14
    0.06
    Negative Logits
     silikon
    -0.99
     karton
    -0.96
     viendra
    -0.95
     exé
    -0.95
     provoque
    -0.90
     pama
    -0.86
     keramik
    -0.82
     susun
    -0.81
     kafe
    -0.81
     véhic
    -0.81
    POSITIVE LOGITS
     gonna
    0.67
     supposed
    0.66
     able
    0.65
     considered
    0.64
     taken
    0.64
     shown
    0.62
     allowed
    0.60
     deemed
    0.60
     actually
    0.59
     going
    0.59
    Activations Density 0.546%

    No Known Activations