© 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. 5305
    Prev
    Next
    INDEX
    Explanations

    information related to events and promotions happening in a community or locality

    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
    2034
    +0.28
    0.9%
    1535
    +0.15
    0.5%
    1403
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.28
    0.04
    1403
    +0.15
    0.02
    1535
    +0.14
    0.04
    Negative Logits
     churrasco
    -0.83
     Endlich
    -0.74
     Áng
    -0.73
     Mejía
    -0.71
     azule
    -0.71
     ujedno
    -0.71
     Leurs
    -0.70
    bonsoir
    -0.70
     viciss
    -0.69
     Darío
    -0.69
    POSITIVE LOGITS
    <eos>
    0.71
     bross
    0.66
     Alternatively
    0.63
     lts
    0.61
    <bos>
    0.58
     esercit
    0.57
     Also
    0.57
    ↵↵
    0.53
    vaila
    0.53
     altrimenti
    0.52
    Activations Density 0.193%

    No Known Activations