© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7652
    Prev
    Next
    INDEX
    Explanations

    phrases related to software development methodologies, specifically focusing on pre-order levels and pre-written reflections

    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
    1059
    +0.13
    0.4%
    1194
    +0.10
    0.4%
    568
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1059
    +0.13
    0.04
    1194
    +0.10
    0.03
    568
    +0.10
    0.04
    Negative Logits
     heapq
    -0.85
     pymysql
    -0.77
     hashlib
    -0.76
     pylab
    -0.70
     pathlib
    -0.68
     pymongo
    -0.61
     shutil
    -0.60
     zipfile
    -0.59
     smtplib
    -0.58
     tempfile
    -0.58
    POSITIVE LOGITS
     prec
    1.14
     prer
    1.11
     socie
    1.09
     canel
    1.09
     dises
    1.08
     nutr
    1.07
     pessi
    1.05
     vito
    1.04
     huma
    1.04
     PRE
    1.03
    Activations Density 0.061%

    No Known Activations