© 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 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. 10964
    Prev
    Next
    INDEX
    Explanations

    descriptions of mechanical support structures and activities related to anchoring boats or structures

    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
    1385
    +0.17
    0.5%
    1352
    +0.08
    0.2%
    163
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.17
    0.05
    1352
    +0.08
    0.05
    724
    +0.08
    0.04
    Negative Logits
     embra
    -1.49
     overla
    -1.30
     emphat
    -1.30
     pessi
    -1.28
     strick
    -1.28
     dispen
    -1.26
     scrat
    -1.22
     igno
    -1.21
     Keny
    -1.21
     accla
    -1.21
    POSITIVE LOGITS
     stability
    0.74
     weight
    0.71
     supports
    0.66
     support
    0.66
     holding
    0.64
     sturdy
    0.64
     stable
    0.63
     withstand
    0.63
     supporting
    0.62
     structure
    0.62
    Activations Density 0.373%

    No Known Activations