© 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. 4368
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical procedures and family relationships

    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
    674
    +0.18
    0.5%
    509
    +0.18
    0.5%
    764
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.18
    0.07
    207
    +0.18
    0.05
    942
    +0.12
    0.05
    Negative Logits
     fta
    -2.25
     wien
    -2.22
     effe
    -2.19
     guarante
    -2.17
     increa
    -2.15
     mef
    -2.15
     „,
    -2.14
     inev
    -2.13
     emphat
    -2.13
     fte
    -2.12
    POSITIVE LOGITS
     my
    0.72
     protect
    0.72
    .
    0.70
     survive
    0.70
     him
    0.69
    ...
    0.69
    ..
    0.68
     her
    0.67
    …
    0.67
     she
    0.67
    Activations Density 0.430%

    No Known Activations