© 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. 3774
    Prev
    Next
    INDEX
    Explanations

    information related to news events and reports

    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
    674
    +0.46
    3.5%
    1741
    +0.07
    0.6%
    1870
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.46
    0.27
    800
    +0.07
    0.28
    1403
    +0.05
    0.24
    Negative Logits
     unspeak
    -3.53
     reluct
    -3.35
     shenan
    -3.18
     disagre
    -3.17
     unlaw
    -3.11
     apprehen
    -3.07
     disgra
    -3.00
     impra
    -2.99
     impractica
    -2.98
     unwarran
    -2.97
    POSITIVE LOGITS
    <bos>
    13.81
    Autoritní
    2.31
    expandindo
    2.26
     betweenstory
    2.26
    GEBURTSDATUM
    2.21
     Paglinawan
    2.10
     Administrativna
    2.07
    تقاوى
    2.04
     Italijani
    2.02
     Италијани
    1.94
    Activations Density 0.087%

    No Known Activations