© 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. 6439
    Prev
    Next
    INDEX
    Explanations

    references to instances or occurrences of specific concepts

    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
    871
    +0.16
    0.7%
    597
    +0.15
    0.6%
    1026
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    597
    +0.16
    0.02
    78
    +0.15
    0.02
    1026
    +0.15
    0.02
    Negative Logits
    Sau
    -0.53
     Sau
    -0.51
    sau
    -0.47
    ナソニック
    -0.43
    Gavin
    -0.41
    jetivo
    -0.40
    jetivos
    -0.40
     <=",
    -0.40
    Hay
    -0.38
    رياض
    -0.38
    POSITIVE LOGITS
     Instance
    1.20
     instance
    1.11
    instance
    1.04
     Instances
    1.04
     instances
    1.00
    Instance
    0.98
    instances
    0.94
     INSTANCE
    0.88
     getInstance
    0.87
    GetInstance
    0.86
    Activations Density 0.106%

    No Known Activations