© 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. 5863
    Prev
    Next
    INDEX
    Explanations

    text related to technical instructions or 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
    1262
    +0.12
    0.4%
    577
    +0.10
    0.3%
    605
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1262
    +0.12
    0.03
    1081
    +0.10
    0.04
    615
    +0.10
    0.02
    Negative Logits
     esboço
    -0.61
     îna
    -0.51
     «<
    -0.50
     (,
    -0.50
     afo
    -0.48
    IsContent
    -0.47
     manquante
    -0.47
     amélior
    -0.47
    ThroughAttribute
    -0.45
     templ
    -0.45
    POSITIVE LOGITS
     ''}
    0.63
    TokenNameLBRACE
    0.59
     Souha
    0.57
    (">>
    0.57
     romero
    0.56
     granada
    0.54
    jinal
    0.53
     Toujours
    0.53
     hias
    0.52
     accepte
    0.51
    Activations Density 0.185%

    No Known Activations