© 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. 1969
    Prev
    Next
    INDEX
    Explanations

    different specific locations and the activities or features related to those locations

    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
    1108
    +0.13
    0.4%
    381
    +0.10
    0.3%
    946
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.13
    0.02
    946
    +0.10
    0.05
    1338
    +0.10
    0.05
    Negative Logits
     shenan
    -2.29
     reluct
    -2.18
     affor
    -2.13
     milf
    -2.08
     intersper
    -2.07
     unspeak
    -2.03
     disagre
    -2.01
     snoopy
    -1.98
     impra
    -1.96
     apprehen
    -1.95
    POSITIVE LOGITS
    <bos>
    1.00
     PLWABN
    0.96
    Conheça
    0.93
    Consejos
    0.93
     Paglinawan
    0.90
    astéro
    0.88
    Confira
    0.86
    Atención
    0.85
    Dicas
    0.85
    Elaboración
    0.83
    Activations Density 0.689%

    No Known Activations