Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 590
    Prev
    Next
    INDEX
    Explanations

    steps or instructions related to setting up or configuring a system or application

    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
    453
    +0.10
    0.3%
    876
    +0.09
    0.3%
    1510
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    267
    +0.10
    0.03
    646
    +0.09
    0.02
    836
    +0.08
    0.01
    Negative Logits
     Juf
    -1.04
     Darío
    -1.04
     Áng
    -1.04
     intersper
    -1.04
     hcm
    -1.03
     depic
    -1.00
     Palembang
    -0.99
     saar
    -0.98
     maneu
    -0.98
     pamph
    -0.98
    POSITIVE LOGITS
    submit
    0.71
     finally
    0.70
     submit
    0.68
    EndInit
    0.64
    finally
    0.62
    SaveChangesAsync
    0.61
     Finally
    0.60
     AssemblyVersion
    0.60
    QPushButton
    0.59
     finished
    0.58
    Activations Density 0.174%

    No Known Activations