© 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. 6218
    Prev
    Next
    INDEX
    Explanations

    locations or places mentioned in the text

    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
    1013
    +0.16
    0.5%
    2034
    +0.14
    0.4%
    1842
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.16
    0.08
    227
    +0.14
    0.08
    1441
    +0.14
    0.07
    Negative Logits
     maig
    -0.80
    expandindo
    -0.68
    UnusedPrivate
    -0.67
     Ottobre
    -0.63
     patin
    -0.62
     spie
    -0.62
     PeEnEo
    -0.62
    Läh
    -0.61
     rhum
    -0.61
     convient
    -0.60
    POSITIVE LOGITS
     unwarran
    1.04
     maneu
    0.97
     withal
    0.96
     gaily
    0.94
     unspeak
    0.91
     unve
    0.89
     disagre
    0.89
     tolerably
    0.89
     apprehen
    0.88
     increa
    0.86
    Activations Density 0.300%

    No Known Activations