© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7249
    Prev
    Next
    INDEX
    Explanations

    mentions of measurements or comparisons between measurements

    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
    752
    +0.15
    0.5%
    1967
    +0.12
    0.4%
    1334
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.15
    0.06
    1334
    +0.12
    0.05
    68
    +0.10
    0.04
    Negative Logits
     fatis
    -0.76
     incess
    -0.74
     pecuni
    -0.73
     whofe
    -0.71
     caufe
    -0.71
     defire
    -0.70
     fupp
    -0.69
     ftre
    -0.67
     difp
    -0.67
     reafon
    -0.66
    POSITIVE LOGITS
     each
    0.63
     the
    0.55
     these
    0.54
     your
    0.53
     of
    0.50
     those
    0.49
     any
    0.49
     Of
    0.48
     our
    0.48
     their
    0.47
    Activations Density 0.329%

    No Known Activations