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

    Neuronpedia

    Jacobian LensNEW
    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. 13728
    Prev
    Next
    INDEX
    Explanations

    instances where the text talks about specific quantitative amounts or comparisons

    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
    897
    +0.12
    0.4%
    849
    +0.12
    0.4%
    662
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    849
    +0.12
    0.02
    897
    +0.12
    0.02
    662
    +0.11
    0.02
    Negative Logits
    OnDelete
    -0.43
     Feind
    -0.43
    Tenure
    -0.42
     Cou
    -0.41
    Rng
    -0.41
     pymongo
    -0.40
     Montag
    -0.40
    $+$
    -0.40
     Heber
    -0.39
    +}\
    -0.39
    POSITIVE LOGITS
     barely
    0.71
     hardly
    0.70
     autorytatywna
    0.70
     haast
    0.70
     Hardly
    0.69
     nutella
    0.66
     scarcely
    0.65
    Життєпис
    0.62
     Bárbara
    0.60
    Біографія
    0.58
    Activations Density 0.083%

    No Known Activations