© 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 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. 14828
    Prev
    Next
    INDEX
    Explanations

    information related to network setup and configurations

    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
    1967
    +0.21
    0.7%
    764
    +0.20
    0.6%
    227
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    630
    +0.21
    0.03
    227
    +0.20
    0.04
    1343
    +0.15
    0.04
    Negative Logits
    Apesar
    -0.86
    <bos>
    -0.85
    معرفی
    -0.80
    Além
    -0.79
    IndentedString
    -0.76
    Ainda
    -0.76
    ویژگی
    -0.75
    Após
    -0.75
    حوالہ
    -0.74
    Dicas
    -0.74
    POSITIVE LOGITS
     emphat
    2.25
     ?...
    2.15
     encomp
    2.05
     increa
    2.02
     inev
    2.02
     !...
    1.97
     guarante
    1.94
     depic
    1.93
     intersper
    1.91
     uninten
    1.85
    Activations Density 0.163%

    No Known Activations