© 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. 7405
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming

    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
    227
    +0.15
    0.5%
    674
    +0.14
    0.4%
    872
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1411
    +0.15
    0.03
    1150
    +0.14
    0.02
    1799
    +0.13
    0.02
    Negative Logits
     alkoh
    -0.96
     silikon
    -0.92
     antik
    -0.84
     mikrofon
    -0.84
     bunda
    -0.83
     Kategor
    -0.82
     matel
    -0.82
     panik
    -0.82
     akut
    -0.80
     karton
    -0.79
    POSITIVE LOGITS
     enlightening
    0.71
     enlight
    0.71
    <bos>
    0.66
     dismant
    0.59
     enlighten
    0.59
     delve
    0.59
     acquaint
    0.58
     summarizing
    0.58
     underval
    0.57
     implore
    0.57
    Activations Density 0.370%

    No Known Activations