© 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. 791
    Prev
    Next
    INDEX
    Explanations

    solutions to systemic issues or social problems

    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
    1253
    +0.10
    0.3%
    1120
    +0.08
    0.2%
    872
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    870
    +0.10
    0.04
    1114
    +0.08
    0.03
    527
    +0.08
    0.04
    Negative Logits
     reluct
    -2.25
     emphat
    -2.25
     maneu
    -2.19
     indestru
    -2.17
     accla
    -2.17
     depic
    -2.10
     inev
    -2.07
     increa
    -2.04
     disagre
    -2.01
     encomp
    -2.00
    POSITIVE LOGITS
     should
    0.76
     needs
    0.66
     solutions
    0.65
    ควร
    0.65
    implementation
    0.65
    AssignableFrom
    0.65
     need
    0.64
    GetAxis
    0.64
     would
    0.63
     could
    0.63
    Activations Density 0.462%

    No Known Activations