© 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. 5820
    Prev
    Next
    INDEX
    Explanations

    definitions and explanations

    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
    872
    +0.18
    0.5%
    1150
    +0.13
    0.4%
    198
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.18
    0.08
    520
    +0.13
    0.03
    450
    +0.11
    0.04
    Negative Logits
    alité
    -0.50
     Helf
    -0.49
     sò
    -0.49
     Ueb
    -0.49
     Administrativna
    -0.47
    BASEPATH
    -0.47
    Abit
    -0.47
     DFB
    -0.46
    bewerken
    -0.45
     tâ
    -0.45
    POSITIVE LOGITS
     connotations
    0.75
     connotation
    0.71
     meanings
    0.68
     meaning
    0.65
     definition
    0.60
     usage
    0.58
     tubercle
    0.57
     definitions
    0.56
     synonyms
    0.56
     deschis
    0.56
    Activations Density 0.607%

    No Known Activations