© 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. 13254
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions related to historical events or figures

    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
    184
    +0.24
    1.0%
    1577
    +0.22
    0.9%
    50
    +0.19
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.24
    0.04
    394
    +0.22
    0.06
    1577
    +0.19
    0.09
    Negative Logits
    <bos>
    -1.10
     betweenstory
    -0.87
    AndroidJUnit
    -0.56
     Wikimedijinoj
    -0.55
     Italijani
    -0.55
    abestanden
    -0.53
    脚注の使い方
    -0.52
    AutoScaleMode
    -0.51
    WindowConstants
    -0.48
    انجليز
    -0.47
    POSITIVE LOGITS
     heapq
    0.69
    YMMV
    0.53
    Bereits
    0.47
    Wię
    0.47
    Cześć
    0.43
     hashlib
    0.43
    Hahah
    0.43
    ἀ
    0.42
    Contactez
    0.42
    Kedves
    0.42
    Activations Density 1.565%

    No Known Activations