© 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. 11007
    Prev
    Next
    INDEX
    Explanations

    information related to gaming consoles and assorted games

    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
    1343
    +0.28
    0.9%
    1510
    +0.16
    0.5%
    198
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1510
    +0.28
    0.05
    227
    +0.16
    0.07
    1343
    +0.13
    0.06
    Negative Logits
     pamph
    -1.12
     sophistic
    -1.08
     shenan
    -1.06
     unspeak
    -1.03
     cytoplas
    -1.03
     unwarran
    -1.02
     caucasian
    -1.00
     Shakspeare
    -0.98
     gaily
    -0.96
     philosophic
    -0.95
    POSITIVE LOGITS
     fré
    0.61
     espé
    0.59
     assiste
    0.58
     tenden
    0.54
    //*/
    0.54
     estime
    0.53
     fonde
    0.53
     fabrique
    0.52
     circon
    0.51
     impon
    0.51
    Activations Density 0.377%

    No Known Activations