© 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. 13719
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or actions related to official government statements and operations

    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
    453
    +0.14
    0.4%
    1150
    +0.13
    0.4%
    1535
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1506
    +0.14
    0.04
    314
    +0.13
    0.03
    395
    +0.12
    0.04
    Negative Logits
     virtù
    -1.08
     quegli
    -0.99
     ecru
    -0.97
     swarovski
    -0.94
     autunno
    -0.91
    vece
    -0.90
     hairc
    -0.89
     affitto
    -0.86
     oleo
    -0.84
     isSuccess
    -0.82
    POSITIVE LOGITS
    Dalam
    0.60
    dalam
    0.59
    Odpo
    0.57
    Història
    0.56
    Conteúdo
    0.55
     Fö
    0.55
     Lorsqu
    0.54
    Mű
    0.54
     În
    0.54
    Atsauces
    0.54
    Activations Density 0.138%

    No Known Activations