© 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 EvalsExportsinterp-engineNEWAPI 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. 16267
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional or symbolic meanings

    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
    896
    +0.17
    0.6%
    1233
    +0.16
    0.6%
    680
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    896
    +0.17
    0.03
    1233
    +0.16
    0.04
    196
    +0.15
    0.03
    Negative Logits
    Parcelize
    -0.47
     يونيو
    -0.46
    anceled
    -0.44
    UnitTesting
    -0.44
     dignidad
    -0.43
    SetActive
    -0.43
    chengladbach
    -0.42
    겪
    -0.41
     يوليو
    -0.41
    lencia
    -0.41
    POSITIVE LOGITS
     heart
    1.30
    heart
    1.25
     HEART
    1.20
    Heart
    1.18
     Heart
    1.17
    HEART
    1.16
     hearts
    1.09
    hearts
    1.03
    Hearts
    1.00
     cuore
    0.90
    Activations Density 0.077%

    No Known Activations