© 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. 6344
    Prev
    Next
    INDEX
    Explanations

    texts related to a musical artist's extensive discography and output

    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
    690
    +0.11
    0.3%
    1415
    +0.08
    0.2%
    297
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2005
    +0.11
    0.03
    1415
    +0.08
    0.02
    870
    +0.08
    0.04
    Negative Logits
     Souha
    -0.78
     cahier
    -0.71
     Vå
    -0.67
     quæ
    -0.67
     Meille
    -0.66
     Præ
    -0.66
     compréhen
    -0.63
     Quelques
    -0.63
     quoique
    -0.62
     Présentation
    -0.62
    POSITIVE LOGITS
     overwhelm
    0.70
     overwhelming
    0.64
     overwhel
    0.64
     overloading
    0.58
     overload
    0.56
     overwhelmed
    0.56
     overkill
    0.56
     clogging
    0.56
     overloaded
    0.51
     saturation
    0.50
    Activations Density 0.826%

    No Known Activations