© 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. 6148
    Prev
    Next
    INDEX
    Explanations

    references to physical gate structures or locations

    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
    1983
    +0.13
    0.6%
    805
    +0.13
    0.6%
    1565
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1565
    +0.13
    0.02
    1983
    +0.13
    0.02
    805
    +0.12
    0.02
    Negative Logits
     оригіналу
    -0.65
     bulunabilir
    -0.55
    rrggbb
    -0.50
    Millan
    -0.50
    tinyos
    -0.49
     كومونز
    -0.48
    Peru
    -0.45
    crapers
    -0.45
     MainAxisSize
    -0.45
    sieur
    -0.44
    POSITIVE LOGITS
     gate
    1.51
     Gate
    1.47
     gates
    1.40
    Gate
    1.40
     Gates
    1.35
    gate
    1.33
    Gates
    1.30
    gates
    1.25
     GATE
    1.19
    GATE
    1.16
    Activations Density 0.110%

    No Known Activations