© 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. 1078
    Prev
    Next
    INDEX
    Explanations

    conditional statements related to specific conditions or circumstances

    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
    1042
    +0.10
    0.3%
    674
    +0.09
    0.2%
    1776
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1438
    +0.10
    0.04
    215
    +0.09
    0.04
    1776
    +0.08
    0.03
    Negative Logits
     pymysql
    -0.84
     smtplib
    -0.78
     psycopg
    -0.75
     pymongo
    -0.73
     pylab
    -0.73
     heapq
    -0.72
    mainwindow
    -0.65
     hcm
    -0.61
     arthur
    -0.61
     greece
    -0.59
    POSITIVE LOGITS
     needed
    0.67
     necessary
    0.62
    needed
    0.57
     available
    0.55
     appropriate
    0.53
     NEEDED
    0.53
    necessary
    0.53
     warranted
    0.53
     iesp
    0.51
     applicable
    0.50
    Activations Density 0.306%

    No Known Activations