© 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. 12801
    Prev
    Next
    INDEX
    Explanations

    alphanumeric codes and technical information like software version numbers and release names

    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
    1978
    +0.18
    0.6%
    1967
    +0.17
    0.5%
    478
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1978
    +0.18
    0.04
    994
    +0.17
    0.03
    1597
    +0.14
    0.02
    Negative Logits
     unspeak
    -1.54
     pamph
    -1.45
     shenan
    -1.35
     Shakspeare
    -1.31
     Illus
    -1.29
     Whence
    -1.29
     melange
    -1.28
     impractica
    -1.28
     indestru
    -1.27
     indescri
    -1.26
    POSITIVE LOGITS
     alkoh
    1.55
     elek
    1.38
     makro
    1.35
     hek
    1.31
     kram
    1.31
     plak
    1.31
     kran
    1.30
     karton
    1.27
     utop
    1.27
     behar
    1.26
    Activations Density 0.099%

    No Known Activations