Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1212
    Prev
    Next
    INDEX
    Explanations

    code snippets related to server responses in HTML

    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
    +0.16
    0.5%
    453
    +0.12
    0.4%
    876
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1356
    +0.16
    0.02
    1678
    +0.12
    0.02
    1018
    +0.12
    0.01
    Negative Logits
     розта
    -0.68
    自带
    -0.65
    的对象
    -0.59
    其实是
    -0.57
    віть
    -0.57
    完成后
    -0.57
     сегодняш
    -0.57
    的参数
    -0.57
     сьогодні
    -0.56
    的任务
    -0.55
    POSITIVE LOGITS
     magis
    1.25
     habet
    1.19
     quæ
    1.13
     potest
    1.10
    ,<
    1.08
     meis
    1.08
     aen
    1.07
     ciao
    1.07
     dises
    1.06
     !...
    1.06
    Activations Density 0.033%

    No Known Activations