© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12717
    Prev
    Next
    INDEX
    Explanations

    dates and events related to history

    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
    872
    +0.11
    0.3%
    1150
    +0.10
    0.3%
    2034
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    924
    +0.11
    0.06
    872
    +0.10
    0.07
    1445
    +0.09
    0.07
    Negative Logits
     abnorm
    -1.06
     immen
    -1.05
     robus
    -1.05
     dynamis
    -1.04
     interse
    -1.02
     notor
    -1.02
     pessi
    -0.99
     riva
    -0.99
     exem
    -0.98
     solidar
    -0.98
    POSITIVE LOGITS
    <bos>
    1.01
     Basically
    0.83
     Briefly
    0.71
     basically
    0.70
     It
    0.69
    Basically
    0.69
     Essentially
    0.67
     There
    0.65
     According
    0.62
     The
    0.60
    Activations Density 0.588%

    No Known Activations