© 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. 11404
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude towards the audience

    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
    599
    +0.10
    0.3%
    1055
    +0.09
    0.3%
    4
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    862
    +0.10
    0.03
    1055
    +0.09
    0.05
    4
    +0.07
    0.04
    Negative Logits
     ejus
    -0.74
     eorum
    -0.72
     habet
    -0.71
     makro
    -0.66
     potest
    -0.59
     conflic
    -0.58
     tantum
    -0.58
     häm
    -0.58
     silikon
    -0.57
     anta
    -0.56
    POSITIVE LOGITS
     ardour
    0.75
     clamour
    0.71
     ingrat
    0.70
     earnestness
    0.70
     ardor
    0.70
     clamor
    0.66
     indescri
    0.65
     idolat
    0.61
     appreciative
    0.61
     ingenu
    0.61
    Activations Density 0.487%

    No Known Activations