© 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. 1034
    Prev
    Next
    INDEX
    Explanations

    Java code structure related tokens and phrases

    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
    227
    +0.15
    0.5%
    1343
    +0.15
    0.5%
    1967
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.15
    0.04
    1343
    +0.15
    0.04
    981
    +0.14
    0.04
    Negative Logits
     horrend
    -1.02
     intersper
    -0.98
     shenan
    -0.98
     reluct
    -0.94
     apprehen
    -0.93
     impelled
    -0.93
     endeavouring
    -0.92
     gaily
    -0.90
     disagre
    -0.87
     schoolmaster
    -0.87
    POSITIVE LOGITS
    Πηγές
    0.60
     soggior
    0.59
     rimanere
    0.59
     obti
    0.57
     Détails
    0.57
     nonatomic
    0.56
     comprendere
    0.56
     risolvere
    0.56
     quidem
    0.55
     Traduction
    0.54
    Activations Density 0.109%

    No Known Activations