© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6900
    Prev
    Next
    INDEX
    Explanations

    medical terms related to injuries and treatments

    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
    247
    +0.08
    0.2%
    1643
    +0.07
    0.2%
    630
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.08
    0.05
    247
    +0.07
    0.05
    1675
    +0.07
    0.06
    Negative Logits
     emphat
    -0.94
     Bibl
    -0.93
     inev
    -0.92
     effe
    -0.90
     embra
    -0.90
     pixabay
    -0.86
     wien
    -0.85
     increa
    -0.84
     „,
    -0.84
     ?...
    -0.84
    POSITIVE LOGITS
     nor
    0.95
    <bos>
    0.94
     whatsoever
    0.88
     anymore
    0.83
     except
    0.74
    except
    0.65
    nor
    0.63
     anything
    0.63
     unless
    0.62
     anywhere
    0.59
    Activations Density 0.411%

    No Known Activations