© 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. 12965
    Prev
    Next
    INDEX
    Explanations

    transactions/news related to selling and purchasing assets or properties

    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
    1385
    +0.13
    0.4%
    1120
    +0.11
    0.3%
    939
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.13
    0.05
    1754
    +0.11
    0.04
    1385
    +0.11
    0.04
    Negative Logits
     OFDb
    -0.64
    MIDDLEWARE
    -0.52
    responseType
    -0.51
    PYX
    -0.50
     سكانية
    -0.50
    hoedd
    -0.49
    Externé
    -0.48
    (@"%@",
    -0.48
    eql
    -0.46
    #
    -0.46
    POSITIVE LOGITS
     Traité
    0.67
     assets
    0.67
     Présentation
    0.64
     KeyCode
    0.64
     Quelques
    0.63
     Mémoires
    0.63
     Chapitre
    0.61
     Déf
    0.60
     freehold
    0.60
     pleins
    0.59
    Activations Density 0.426%

    No Known Activations