© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13401
    Prev
    Next
    INDEX
    Explanations

    mentions of progress and satisfaction regarding the development of implants and medical trials

    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
    1919
    +0.11
    0.3%
    453
    +0.10
    0.3%
    1510
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.11
    0.06
    1097
    +0.10
    0.05
    888
    +0.10
    0.04
    Negative Logits
     lele
    -1.46
     canel
    -1.41
     tanga
    -1.40
     bordeaux
    -1.39
     kram
    -1.37
     casio
    -1.36
     cannes
    -1.36
     soggior
    -1.36
     mef
    -1.34
     pican
    -1.34
    POSITIVE LOGITS
     says
    0.86
     said
    0.82
     explains
    0.78
     believes
    0.76
    <bos>
    0.76
     noted
    0.76
     explained
    0.74
     describes
    0.72
     hopes
    0.72
     recommends
    0.71
    Activations Density 0.165%

    No Known Activations