© 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. 13443
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numbers or quantities

    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
    776
    +0.12
    0.4%
    1842
    +0.12
    0.4%
    897
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2016
    +0.12
    0.07
    16
    +0.12
    0.07
    161
    +0.12
    0.03
    Negative Logits
    <bos>
    -0.69
     AssemblyCompany
    -0.58
    toHaveBeen
    -0.53
    Ikr
    -0.50
     tartalomajánló
    -0.49
     kaynağından
    -0.48
     eût
    -0.48
     CascadeType
    -0.48
     reú
    -0.47
    fordable
    -0.47
    POSITIVE LOGITS
     lagar
    0.52
    municipi
    0.51
     Seconde
    0.51
    település
    0.50
     Ə
    0.50
     whom
    0.48
     Ibidem
    0.47
     voglio
    0.47
    SBATCH
    0.47
     inverte
    0.47
    Activations Density 0.574%

    No Known Activations