© 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. 2198
    Prev
    Next
    INDEX
    Explanations

    medical terms related to cell health and inflammation

    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
    184
    +0.32
    1.1%
    1577
    +0.22
    0.7%
    1870
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.32
    0.04
    2044
    +0.22
    0.07
    1577
    +0.13
    0.07
    Negative Logits
     utop
    -1.27
     impon
    -1.26
     alkoh
    -1.24
     minimalis
    -1.18
     kosme
    -1.16
     republi
    -1.15
     prega
    -1.13
     hek
    -1.12
     ideolog
    -1.12
     apparti
    -1.11
    POSITIVE LOGITS
     and
    0.83
     poetical
    0.70
     Ename
    0.68
     Engraved
    0.66
     CONDUIT
    0.66
     withal
    0.65
     friable
    0.64
     ItemType
    0.64
     Shakspeare
    0.63
     ascetic
    0.63
    Activations Density 0.449%

    No Known Activations