© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12374
    Prev
    Next
    INDEX
    Explanations

    descriptions of cafes and animal-themed eateries

    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
    198
    +0.12
    0.4%
    736
    +0.11
    0.3%
    227
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.12
    0.07
    1380
    +0.11
    0.02
    944
    +0.10
    0.03
    Negative Logits
     solidar
    -1.36
     alkoh
    -1.26
     Rektor
    -1.25
     kosme
    -1.21
     utop
    -1.21
     makro
    -1.18
     kram
    -1.18
     ideolog
    -1.15
     minimalis
    -1.15
     anse
    -1.14
    POSITIVE LOGITS
     unspeak
    1.11
     withal
    1.08
     disagre
    1.05
     tolerably
    1.04
     indestru
    1.01
     shewn
    1.01
     impelled
    0.96
     indescri
    0.94
     apprehen
    0.91
     flocc
    0.89
    Activations Density 0.586%

    No Known Activations