© 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. 7263
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasons or causes

    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
    1438
    +0.14
    0.5%
    1839
    +0.13
    0.5%
    1691
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1691
    +0.14
    0.05
    18
    +0.13
    0.04
    1438
    +0.10
    0.04
    Negative Logits
     Più
    -0.70
     Queste
    -0.69
     Così
    -0.66
     Altri
    -0.65
     Questi
    -0.64
     Molto
    -0.62
     Oltre
    -0.62
     Ciò
    -0.61
     pymysql
    -0.59
     Mentre
    -0.59
    POSITIVE LOGITS
     because
    0.72
     osal
    0.71
     iyon
    0.69
     they
    0.68
     BECAUSE
    0.67
    ECAUSE
    0.65
     Because
    0.62
    because
    0.62
     habang
    0.59
     kapag
    0.58
    Activations Density 0.130%

    No Known Activations