© 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. 14501
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and currency formats

    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
    2019
    +0.21
    0.7%
    1343
    +0.17
    0.5%
    50
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1678
    +0.21
    0.03
    1274
    +0.17
    0.03
    1343
    +0.13
    0.03
    Negative Logits
    的数量
    -0.57
    的基本
    -0.55
    的任务
    -0.54
    的主要
    -0.54
    러한
    -0.53
    的核心
    -0.53
    的行
    -0.53
    的角色
    -0.53
     public
    -0.52
    的首
    -0.52
    POSITIVE LOGITS
     Cfr
    1.33
     §.
    1.28
     grati
    1.25
     embodi
    1.19
     mef
    1.19
     haer
    1.17
     Altri
    1.15
     gmbh
    1.13
     „,
    1.13
     napoli
    1.13
    Activations Density 0.077%

    No Known Activations