© 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. 5578
    Prev
    Next
    INDEX
    Explanations

    mentions of significant or notable events

    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
    674
    +0.43
    1.6%
    604
    +0.16
    0.6%
    344
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.43
    0.06
    344
    +0.16
    0.02
    468
    +0.13
    0.04
    Negative Logits
     fameux
    -0.79
     KeyCode
    -0.78
     velour
    -0.78
     ecru
    -0.76
     tupperware
    -0.75
     génie
    -0.74
     DataType
    -0.74
     minValue
    -0.74
     Washable
    -0.73
     Ornaments
    -0.73
    POSITIVE LOGITS
     ideolog
    1.16
     minimalis
    1.11
     solidar
    1.02
     kosme
    1.01
     praktik
    0.98
     konserv
    0.95
     alkoh
    0.94
     notor
    0.93
     kön
    0.93
     kritis
    0.91
    Activations Density 0.989%

    No Known Activations