© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14304
    Prev
    Next
    INDEX
    Explanations

    instances where a phrase or word structure repeats

    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
    1343
    +0.10
    0.3%
    856
    +0.10
    0.3%
    1967
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1862
    +0.10
    0.02
    1856
    +0.10
    0.02
    446
    +0.09
    0.02
    Negative Logits
     smtplib
    -0.78
     Février
    -0.67
     pymysql
    -0.65
     hashlib
    -0.65
     ecru
    -0.61
    setToolTipText
    -0.58
     BaseEntity
    -0.58
    unisex
    -0.58
     ItemType
    -0.58
     velour
    -0.58
    POSITIVE LOGITS
     konflikt
    0.59
     peniten
    0.58
     priva
    0.56
     asfal
    0.56
     filma
    0.56
     kontra
    0.55
     respek
    0.55
     kompres
    0.54
     stras
    0.54
     recenz
    0.54
    Activations Density 0.060%

    No Known Activations