© 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. 12430
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or surnames

    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
    227
    +0.11
    0.3%
    1177
    +0.08
    0.2%
    1843
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.11
    0.04
    227
    +0.08
    0.04
    1843
    +0.08
    0.02
    Negative Logits
     unlaw
    -0.60
     Initialise
    -0.56
     subgoals
    -0.51
     panasonic
    -0.51
     intersper
    -0.48
     Incenti
    -0.47
     Functionality
    -0.46
     Standardi
    -0.46
     underval
    -0.46
    нрави
    -0.45
    POSITIVE LOGITS
     family
    0.73
     familie
    0.65
     propOrder
    0.64
     famiglia
    0.64
     manuten
    0.59
     siblings
    0.59
    iseite
    0.57
    family
    0.57
     Jerusal
    0.56
     Famille
    0.56
    Activations Density 0.120%

    No Known Activations