© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 6702
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to environmental science

    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
    1343
    +0.24
    0.8%
    876
    +0.21
    0.7%
    1177
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.24
    0.06
    1343
    +0.21
    0.05
    283
    +0.14
    0.01
    Negative Logits
    <bos>
    -1.16
     in
    -1.07
     for
    -1.01
     as
    -1.01
     on
    -1.01
     can
    -1.00
     to
    -1.00
    .
    -0.98
     so
    -0.98
     with
    -0.98
    POSITIVE LOGITS
     alkoh
    2.65
     marte
    2.63
     milano
    2.58
     elek
    2.52
     franz
    2.51
     cannes
    2.48
     aquare
    2.48
     incess
    2.47
     ordina
    2.46
     kram
    2.46
    Activations Density 0.190%

    No Known Activations