© 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. 14788
    Prev
    Next
    INDEX
    Explanations

    mentions of specific numerical values in contexts related to technology, tutorials or instructions

    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
    1961
    +0.13
    0.4%
    1334
    +0.13
    0.4%
    1896
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1334
    +0.13
    0.04
    1961
    +0.13
    0.04
    545
    +0.12
    0.03
    Negative Logits
     móg
    -0.77
    ;;)
    -0.69
     plis
    -0.64
     !...
    -0.63
    uvres
    -0.61
    esss
    -0.60
     wong
    -0.59
    OfClass
    -0.59
    :))
    -0.59
    :,,
    -0.58
    POSITIVE LOGITS
    Mə
    0.71
    árbol
    0.63
    Misión
    0.60
    jetzt
    0.59
    Ilustra
    0.58
    Çok
    0.58
    símbolo
    0.57
    momento
    0.56
    mbggenerated
    0.56
    Haben
    0.55
    Activations Density 0.155%

    No Known Activations