© 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. 11805
    Prev
    Next
    INDEX
    Explanations

    expressions of good luck and supportiveness

    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
    764
    +0.08
    0.2%
    1731
    +0.08
    0.2%
    651
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    4
    +0.08
    0.03
    839
    +0.08
    0.02
    2016
    +0.07
    0.03
    Negative Logits
     Ibidem
    -0.74
     Græ
    -0.72
     Præ
    -0.71
     Hæ
    -0.67
     Idem
    -0.64
     Pozna
    -0.59
     ideolog
    -0.58
     Departement
    -0.57
     uhr
    -0.55
     Strukt
    -0.55
    POSITIVE LOGITS
    脚注の使い方
    0.65
    quante
    0.54
    ientôt
    0.52
    chequer
    0.51
    ffl
    0.51
     AssemblyVersion
    0.50
    thello
    0.48
     restful
    0.47
     wherever
    0.47
    lottes
    0.47
    Activations Density 0.171%

    No Known Activations