© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 952
    Prev
    Next
    INDEX
    Explanations

    information related to net worth, rankings, and financial details of individuals and entities

    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
    1343
    +0.23
    0.8%
    50
    +0.21
    0.7%
    1108
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.23
    0.04
    895
    +0.21
    0.03
    50
    +0.12
    0.03
    Negative Logits
    ,
    -1.00
    ，
    -0.98
    、
    -0.97
     to
    -0.96
    用
    -0.95
    .
    -0.95
     and
    -0.94
    和
    -0.94
    の
    -0.94
    一
    -0.94
    POSITIVE LOGITS
     Cfr
    2.35
     embra
    2.15
     Sén
    2.08
     rafra
    2.04
     confé
    2.03
     Juf
    2.02
     accla
    1.99
     Augu
    1.98
     vôtre
    1.97
     Mlle
    1.95
    Activations Density 0.132%

    No Known Activations