© 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. 4046
    Prev
    Next
    INDEX
    Explanations

    terms related to the classification of early human ancestors and hominids

    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
    596
    +0.12
    0.5%
    1971
    +0.12
    0.5%
    553
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1971
    +0.12
    0.02
    1637
    +0.12
    0.02
    1103
    +0.12
    0.02
    Negative Logits
     vodi
    -0.49
     Medford
    -0.45
    Sklici
    -0.45
     zdrav
    -0.44
     kona
    -0.43
     Roper
    -0.42
     gerekir
    -0.41
     Wheeling
    -0.41
    Passo
    -0.41
     zra
    -0.40
    POSITIVE LOGITS
     Hom
    1.46
     hom
    1.42
    Hom
    1.31
    hom
    1.24
     HOM
    1.19
    HOM
    1.02
     homo
    0.91
     Homo
    0.90
     heter
    0.88
     homogen
    0.88
    Activations Density 0.113%

    No Known Activations