© 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. 14863
    Prev
    Next
    INDEX
    Explanations

    quotes from spokespersons or spokespeople

    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
    1150
    +0.17
    0.5%
    1343
    +0.12
    0.4%
    453
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    888
    +0.17
    0.07
    1150
    +0.12
    0.04
    1650
    +0.12
    0.05
    Negative Logits
     swarovski
    -1.41
     murano
    -1.40
     bordeaux
    -1.37
     vespa
    -1.35
     eiffel
    -1.32
     lidl
    -1.31
     ecru
    -1.30
     thermomix
    -1.29
     ibiza
    -1.26
     cabrio
    -1.22
    POSITIVE LOGITS
     said
    0.67
     confirmed
    0.66
     explained
    0.63
     told
    0.63
    Datuak
    0.62
    ագրություններ
    0.59
     stated
    0.59
     estekak
    0.57
     confirm
    0.55
    Παραπομπές
    0.55
    Activations Density 0.318%

    No Known Activations