© 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 EvalsExportsinterp-engineNEWAPI 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. 4782
    Prev
    Next
    INDEX
    Explanations

    scheduled events and performance details

    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
    +0.35
    1.2%
    1842
    +0.15
    0.5%
    1343
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.35
    0.02
    1343
    +0.15
    0.02
    137
    +0.14
    0.01
    Negative Logits
     shenan
    -1.02
     apprehen
    -0.91
     unspeak
    -0.85
     reluct
    -0.80
     philanth
    -0.79
     stickied
    -0.78
     pamph
    -0.78
     accla
    -0.76
     Pekan
    -0.76
     practition
    -0.76
    POSITIVE LOGITS
    цездатний
    0.53
    Crossref
    0.53
    &
    0.52
    ContentAsync
    0.51
    DataPropertyName
    0.51
     auctor
    0.50
    ]$}
    0.50
    DateField
    0.50
    ILabel
    0.49
     ºC
    0.49
    Activations Density 0.026%

    No Known Activations