© 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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13864
    Prev
    Next
    INDEX
    Explanations

    acronyms and short forms in uppercase characters that contain the substring "UR."

    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
    506
    +0.14
    0.5%
    577
    +0.12
    0.5%
    1806
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.14
    0.04
    577
    +0.12
    0.03
    1174
    +0.12
    0.02
    Negative Logits
    DockStyle
    -0.53
    toHaveBeenCalled
    -0.48
     Walkover
    -0.48
     half
    -0.47
     provider
    -0.47
     initComponents
    -0.46
     Sam
    -0.45
    ชาย
    -0.44
    LINE
    -0.44
    PROVIDER
    -0.44
    POSITIVE LOGITS
     shur
    1.09
     desir
    1.04
     scrat
    1.03
     embra
    1.01
     inev
    0.97
     excru
    0.96
     increa
    0.96
     fuj
    0.96
     purcha
    0.95
     ?...
    0.94
    Activations Density 0.165%

    No Known Activations