© 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 EvalsExportsinterp-engineNEWAPI 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. 4857
    Prev
    Next
    INDEX
    Explanations

    locations and geographical entities

    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
    1984
    +0.11
    0.3%
    453
    +0.10
    0.3%
    1510
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1654
    +0.11
    0.05
    1043
    +0.10
    0.04
    1510
    +0.10
    0.04
    Negative Logits
    <bos>
    -0.88
     kasarigan
    -0.62
     niestety
    -0.60
    GEBURTSDATUM
    -0.60
    raught
    -0.59
    μως
    -0.58
     chcą
    -0.57
    rictions
    -0.57
     disambiguazione
    -0.56
     tæt
    -0.56
    POSITIVE LOGITS
     alkoh
    0.85
     kosme
    0.82
     soulign
    0.81
     représ
    0.81
     Chapitre
    0.80
     déliv
    0.80
     prétend
    0.78
     imprimer
    0.78
     antik
    0.77
     Kategor
    0.76
    Activations Density 0.172%

    No Known Activations