© 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. 6143
    Prev
    Next
    INDEX
    Explanations

    details about legal battles or disputes

    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
    1577
    +0.24
    0.8%
    1013
    +0.15
    0.5%
    394
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1531
    +0.24
    0.10
    736
    +0.15
    0.15
    946
    +0.14
    0.10
    Negative Logits
     broder
    -1.22
     drap
    -1.20
     cannes
    -1.17
     fers
    -1.16
     utop
    -1.14
     vola
    -1.14
     lende
    -1.12
     marte
    -1.11
     paillettes
    -1.10
     ordina
    -1.09
    POSITIVE LOGITS
     afterwards
    0.71
     later
    0.70
     thereafter
    0.67
     subsequent
    0.66
     venge
    0.64
     again
    0.63
     another
    0.62
     afterward
    0.61
     subsequently
    0.61
     retaliation
    0.60
    Activations Density 4.867%

    No Known Activations